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

    Neuronpedia

    INDEX
    Explanations

    can/could

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :hover
    -0.07
    perf
    -0.07
     ws
    -0.07
    .y
    -0.07
    .s
    -0.07
     fino
    -0.07
    opia
    -0.06
    .x
    -0.06
    jak
    -0.06
    ug
    -0.06
    POSITIVE LOGITS
    造成
    0.07
    无码
    0.07
     네이트
    0.06
     각
    0.06
     keyst
    0.06
    械
    0.06
    努
    0.06
     عامة
    0.05
     #+#
    0.05
     способ
    0.05
    Act Density 0.018%

    No Known Activations