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

    Neuronpedia

    INDEX
    Explanations

    YYYY-MM-DD date format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sealed
    0.40
     Minute
    0.39
     amyl
    0.39
     numberWithFloat
    0.38
    运
    0.38
     Part
    0.37
     amusing
    0.37
     Strength
    0.37
    byn
    0.37
     sealant
    0.36
    POSITIVE LOGITS
    toISOString
    0.44
    Ǧ
    0.42
    +'-
    0.42
    -]+
    0.41
    四大
    0.41
    形
    0.37
     dash
    0.37
     Hokkaido
    0.36
    '=>'','
    0.36
    ]}/${
    0.36
    Act Density 0.009%

    No Known Activations