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

    Neuronpedia

    INDEX
    Explanations

    earlier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kapit
    -0.08
    _wf
    -0.08
     Kob
    -0.07
    ウィ
    -0.07
    _DEPRECATED
    -0.06
    esters
    -0.06
    nerRadius
    -0.06
     offsets
    -0.06
    !***
    -0.06
    REDENTIAL
    -0.06
    POSITIVE LOGITS
    violent
    0.07
     نوع
    0.07
     Email
    0.07
    &W
    0.06
     Lup
    0.06
     combos
    0.06
     bed
    0.06
    lush
    0.06
     Clemson
    0.06
    (nome
    0.06
    Act Density 0.000%

    No Known Activations