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

    Neuronpedia

    INDEX
    Explanations

    complaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FWD
    -0.07
     ASSIGN
    -0.07
    SORT
    -0.07
    ardon
    -0.07
     jerk
    -0.07
     нових
    -0.07
     Rubber
    -0.07
    资格
    -0.06
     sluts
    -0.06
     SearchResult
    -0.06
    POSITIVE LOGITS
     complaining
    0.07
    .Ε
    0.07
     >&
    0.07
    озі
    0.07
     complains
    0.06
    :E
    0.06
    归
    0.06
    于
    0.06
     critically
    0.06
     ؛
    0.06
    Act Density 0.016%

    No Known Activations