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

    Neuronpedia

    INDEX
    Explanations

    isolation and containers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    srv
    -0.07
    routes
    -0.06
    arrants
    -0.06
    こ
    -0.06
     比
    -0.06
    юн
    -0.06
     вина
    -0.06
    _xt
    -0.06
    _ARRAY
    -0.06
    ật
    -0.06
    POSITIVE LOGITS
       ↵
    0.07
     Lit
    0.07
    %"><
    0.07
     grey
    0.07
    _dash
    0.07
     boring
    0.07
     conform
    0.06
    をした
    0.06
     spiked
    0.06
     meiner
    0.06
    Act Density 0.018%

    No Known Activations