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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ფუნქ
    0.63
    <unused584>
    0.62
    <unused683>
    0.62
    例えば
    0.61
    崱
    0.61
    <unused230>
    0.61
    geoType
    0.60
    elevationMap
    0.60
    𝕙
    0.60
    <unused330>
    0.60
    POSITIVE LOGITS
    y
    0.62
    im
    0.59
    on
    0.54
     on
    0.54
     area
    0.54
    at
    0.54
    an
    0.52
    h
    0.51
    u
    0.51
     de
    0.50
    Act Density 0.000%

    No Known Activations