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

    Neuronpedia

    INDEX
    Explanations

    Colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .entry
    -0.07
     сіль
    -0.07
     十
    -0.06
     Location
    -0.06
     Συ
    -0.06
     部
    -0.06
    fifo
    -0.06
     Innovation
    -0.06
    Maintenance
    -0.06
     coincidence
    -0.06
    POSITIVE LOGITS
    jectives
    0.07
    ék
    0.07
     ži
    0.07
    Records
    0.06
    asından
    0.06
    äll
    0.06
    .....
    0.06
    <E
    0.06
     tě
    0.06
    바
    0.06
    Act Density 0.011%

    No Known Activations