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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stefan
    -0.08
    _lift
    -0.07
    _arc
    -0.06
    —which
    -0.06
    (target
    -0.06
    folios
    -0.06
    .pan
    -0.06
    regn
    -0.06
     Texans
    -0.06
     Platform
    -0.06
    POSITIVE LOGITS
    いや
    0.07
     deltaTime
    0.07
    振り
    0.07
     लगभग
    0.06
    誌
    0.06
    }_
    0.06
     concl
    0.06
     ﾍ
    0.06
    _pressed
    0.06
     uso
    0.06
    Act Density 0.007%

    No Known Activations