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

    Neuronpedia

    INDEX
    Explanations

    references to discovery or revelation

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

    find out / find up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heard
    -0.80
     hears
    -0.73
     see
    -0.72
     seeing
    -0.70
     seen
    -0.69
    heard
    -0.68
    Seen
    -0.68
     sees
    -0.67
     hear
    -0.67
     saw
    -0.64
    POSITIVE LOGITS
    principalColumn
    0.57
    TargetException
    0.50
    jsxFileName
    0.48
     autorytatywna
    0.45
     FetchType
    0.45
     Infórmanos
    0.45
     nakalista
    0.45
    stylers
    0.44
    WriteTagHelper
    0.43
    ]=>
    0.43
    Act Density 0.115%

    No Known Activations