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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hints
    -0.06
    idon
    -0.06
     Steps
    -0.06
     bốn
    -0.06
     whisky
    -0.06
    하며
    -0.06
     підтрим
    -0.06
    (J
    -0.06
    645
    -0.06
    ema
    -0.06
    POSITIVE LOGITS
     waivers
    0.07
     personnel
    0.07
    TOR
    0.06
    _DISABLE
    0.06
     publication
    0.06
     стати
    0.06
     publications
    0.06
    ;amp
    0.06
    ologna
    0.06
    angelog
    0.06
    Act Density 0.104%

    No Known Activations