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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     killing
    -0.09
     ಆದ
    -0.09
     soldats
    -0.08
     cita
    -0.08
     aborda
    -0.08
     jadi
    -0.08
     ocas
    -0.08
    梦想
    -0.08
     ಪ್ರವ
    -0.08
    -working
    -0.08
    POSITIVE LOGITS
    ваты
    0.08
     computed
    0.08
    Depends
    0.08
    ার্থী
    0.08
     Depends
    0.08
    /vector
    0.08
    162
    0.08
     Lin
    0.07
     concluded
    0.07
    Answer
    0.07
    Act Density 0.022%

    No Known Activations