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

    Neuronpedia

    INDEX
    Explanations

    references to modifications or alterations

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

    making or affecting changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yer
    -0.41
    oy
    -0.40
     Donnelly
    -0.39
     Moll
    -0.39
     Kaufmann
    -0.37
     Whelan
    -0.36
     club
    -0.35
     cucchiaio
    -0.35
     representatives
    -0.34
    ye
    -0.34
    POSITIVE LOGITS
     modifications
    0.93
     Changes
    0.89
     changes
    0.89
    Changes
    0.88
    changes
    0.83
    Modifications
    0.82
     Modifications
    0.82
    modific
    0.81
     adjustments
    0.81
     additions
    0.80
    Act Density 0.046%

    No Known Activations