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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Miller
    -0.07
     hers
    -0.06
    [offset
    -0.06
    )+'
    -0.06
    cidade
    -0.06
     liken
    -0.06
    idata
    -0.06
     월
    -0.06
     Corm
    -0.05
     GAP
    -0.05
    POSITIVE LOGITS
     ====
    0.07
    STATE
    0.07
    (recv
    0.07
     �
    0.07
    /todo
    0.07
     Mend
    0.07
    iers
    0.06
    (uuid
    0.06
    _Space
    0.06
     محاس
    0.06
    Act Density 0.011%

    No Known Activations