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

    Neuronpedia

    INDEX
    Explanations

    code and digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ippers
    -0.07
    desc
    -0.06
    modify
    -0.06
    �
    -0.06
    _VEC
    -0.06
    -es
    -0.06
    _words
    -0.06
     favourable
    -0.06
    ější
    -0.06
    descricao
    -0.06
    POSITIVE LOGITS
    	pthread
    0.08
     shocked
    0.07
     murdered
    0.07
     저
    0.06
    live
    0.06
     thick
    0.06
     Аз
    0.06
    iyorum
    0.06
     guitarist
    0.06
     additions
    0.06
    Act Density 0.004%

    No Known Activations