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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ford
    -0.07
     randomly
    -0.06
     Fransız
    -0.06
     ölçü
    -0.06
     strings
    -0.06
     buds
    -0.06
     nunca
    -0.06
     $"
    -0.06
     Protest
    -0.06
     кожи
    -0.06
    POSITIVE LOGITS
     regulates
    0.07
    ween
    0.07
    áv
    0.07
    __),
    0.07
    abet
    0.07
    .setLevel
    0.07
     accompany
    0.07
     akin
    0.07
    JKLM
    0.06
    kola
    0.06
    Act Density 0.045%

    No Known Activations