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

    Neuronpedia

    INDEX
    Explanations

    free and open events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indows
    -0.07
     Почему
    -0.07
     FK
    -0.07
     References
    -0.07
     שקלים
    -0.07
    еш
    -0.06
    慆
    -0.06
    ᗢ
    -0.06
    ﺚ
    -0.06
     paternal
    -0.06
    POSITIVE LOGITS
     따른
    0.08
    Roll
    0.07
    .ensure
    0.07
    _recommend
    0.07
    DEFINED
    0.07
    .movie
    0.07
    ILT
    0.07
     nó
    0.06
    ROY
    0.06
     caus
    0.06
    Act Density 0.009%

    No Known Activations