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

    Neuronpedia

    INDEX
    Explanations

    UNITED

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogle
    -0.07
     En
    -0.06
    bersome
    -0.06
    sf
    -0.06
    //!
    -0.06
    、な
    -0.06
     multimedia
    -0.06
    吾
    -0.06
     Yük
    -0.06
    _cnt
    -0.06
    POSITIVE LOGITS
     killers
    0.07
     SAY
    0.06
     Courtney
    0.06
    352
    0.06
    .spin
    0.06
     agitation
    0.06
    '/
    0.06
     branch
    0.06
    itary
    0.06
     {[
    0.06
    Act Density 0.002%

    No Known Activations