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

    Neuronpedia

    INDEX
    Explanations

    peak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resultat
    -0.07
     graphene
    -0.06
    fluid
    -0.06
     охорони
    -0.06
     hóa
    -0.06
     ışık
    -0.06
    ，被
    -0.06
     لي
    -0.06
    .connections
    -0.06
     gü
    -0.06
    POSITIVE LOGITS
     Twilight
    0.07
    (file
    0.06
     strives
    0.06
     wears
    0.06
     IE
    0.06
    _USAGE
    0.06
    -अ
    0.06
    unday
    0.06
     Junk
    0.06
    |=
    0.06
    Act Density 0.008%

    No Known Activations