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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     February
    -0.07
    -*
    -0.06
    .Struct
    -0.06
    ento
    -0.06
    ooks
    -0.06
    variants
    -0.06
    เซ
    -0.06
    ¸
    -0.06
    269
    -0.06
    _parse
    -0.06
    POSITIVE LOGITS
     now
    0.09
    เว
    0.08
    زل
    0.07
     ışık
    0.07
     thinly
    0.07
     сви
    0.07
    nown
    0.06
     prostor
    0.06
    �
    0.06
     velik
    0.06
    Act Density 0.024%

    No Known Activations