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

    Neuronpedia

    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    286
    -0.07
    _ios
    -0.07
     Cons
    -0.06
     Zak
    -0.06
     avoidance
    -0.06
    .itemView
    -0.06
    单
    -0.06
     slaves
    -0.06
    _slots
    -0.06
    Gun
    -0.06
    POSITIVE LOGITS
     інститут
    0.07
     þ
    0.06
    _rho
    0.06
    _upd
    0.06
     frankfurt
    0.06
    questions
    0.06
     """
↵
↵
    0.06
    ';
↵
    0.06
    ?'↵↵
    0.06
    ła
    0.06
    Act Density 0.007%

    No Known Activations