Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to social or political issues, particularly surrounding equality and familial dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by a quotation

    np_acts-logits-general · gemini-2.0-flash

    reporting or stating facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endpush
    -0.73
     Signalez
    -0.71
    XtraGrid
    -0.69
    endphp
    -0.68
     '\\;'
    -0.67
     ModelExpression
    -0.65
    OGND
    -0.64
     Exactos
    -0.63
    postsleuth
    -0.63
     MonoBehaviour
    -0.62
    POSITIVE LOGITS
     saying
    1.36
     stating
    1.02
     diciendo
    0.99
     noting
    0.96
     afir
    0.93
    saying
    0.92
     citing
    0.92
     mengatakan
    0.91
     dicendo
    0.89
     said
    0.85
    Act Density 0.468%

    No Known Activations