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

    Neuronpedia

    INDEX
    Explanations

    Language learning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Для
    -0.07
    可以
    -0.07
    �州
    -0.07
     negate
    -0.06
    clared
    -0.06
     можна
    -0.06
    ности
    -0.06
     свого
    -0.06
    gere
    -0.06
     sexo
    -0.06
    POSITIVE LOGITS
     kullan
    0.07
    .ent
    0.07
     CFR
    0.07
    STE
    0.06
     инвести
    0.06
     hospodář
    0.06
    .setParent
    0.06
    楽
    0.06
    allee
    0.06
    ilent
    0.06
    Act Density 0.031%

    No Known Activations