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

    Neuronpedia

    INDEX
    Explanations

    Remedies & supplements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oth
    -0.07
    ُس
    -0.07
     Self
    -0.07
    idis
    -0.07
     Pad
    -0.07
     съ
    -0.06
     pointed
    -0.06
    乙
    -0.06
    附近
    -0.06
     多
    -0.06
    POSITIVE LOGITS
    OTHER
    0.07
    :=
    0.07
     BUG
    0.06
     breasts
    0.06
    %";↵
    0.06
     conhe
    0.06
     strict
    0.06
     свет
    0.06
     apple
    0.06
     μέχρι
    0.06
    Act Density 0.015%

    No Known Activations