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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wildlife
    -0.08
    SignIn
    -0.07
    unds
    -0.07
    Fund
    -0.06
     explain
    -0.06
    ツ
    -0.06
     Furn
    -0.06
    _completion
    -0.06
     dif
    -0.06
    .about
    -0.06
    POSITIVE LOGITS
     जव
    0.07
     評
    0.07
    şiv
    0.06
     accession
    0.06
    .rabbit
    0.06
    :inline
    0.06
    /components
    0.06
    caff
    0.06
     meilleur
    0.06
    'yi
    0.06
    Act Density 0.035%

    No Known Activations