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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　　　　
    -0.06
     stap
    -0.06
    .equalTo
    -0.06
    samp
    -0.06
     plaintiffs
    -0.06
     ～
    -0.06
     ديگر
    -0.06
    `}
    -0.06
     Sir
    -0.06
    ดน
    -0.06
    POSITIVE LOGITS
    _ALERT
    0.07
    [
    0.07
     DAY
    0.06
    .Rollback
    0.06
    坊
    0.06
     повітря
    0.06
     unrecognized
    0.06
    .TRA
    0.06
    /blue
    0.06
    _Style
    0.06
    Act Density 0.000%

    No Known Activations