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

    Neuronpedia

    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NB
    -0.07
    Courier
    -0.06
    ıyorlar
    -0.06
    scp
    -0.06
    -widget
    -0.06
    าม
    -0.06
    _baseline
    -0.06
    ool
    -0.06
    -М
    -0.06
    ]);↵
    -0.05
    POSITIVE LOGITS
    ٨
    0.06
     универ
    0.06
     approaching
    0.06
    (outputs
    0.06
     σχέ
    0.06
     average
    0.06
     epid
    0.06
     Ing
    0.06
    PURE
    0.06
    тий
    0.06
    Act Density 0.084%

    No Known Activations