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

    Neuronpedia

    INDEX
    Explanations

    Bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Avg
    -0.06
    omore
    -0.06
    ::::::
    -0.06
    Executive
    -0.06
    ův
    -0.06
    าป
    -0.06
     помещ
    -0.06
    Junior
    -0.05
    coding
    -0.05
    _size
    -0.05
    POSITIVE LOGITS
     undue
    0.07
     odpově
    0.07
    ilig
    0.07
    .userdetails
    0.06
     Accountability
    0.06
     인터
    0.06
     kadar
    0.06
    /accounts
    0.06
    .yy
    0.06
     Jetzt
    0.06
    Act Density 0.003%

    No Known Activations