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

    Neuronpedia

    INDEX
    Explanations

    places and associated topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.79
     этот
    0.73
    u
    0.72
    но
    0.70
    at
    0.65
    ной
    0.63
    teenth
    0.63
    блема
    0.62
    this
    0.60
    nej
    0.60
    POSITIVE LOGITS
    。
    0.63
    IS
    0.59
    Protein
    0.57
    ときの
    0.57
     tubes
    0.57
    Unsere
    0.56
    .。
    0.56
    データ
    0.55
     luxe
    0.55
     be
    0.55
    Act Density 0.006%

    No Known Activations