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

    Neuronpedia

    INDEX
    Explanations

    recency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    absolute
    -0.07
    Unnamed
    -0.07
     Combat
    -0.07
     FIXME
    -0.07
     Personal
    -0.06
     combat
    -0.06
     Ultra
    -0.06
     pre
    -0.06
     tail
    -0.06
     promises
    -0.06
    POSITIVE LOGITS
     Vul
    0.06
    ـــ
    0.06
    _relation
    0.06
    -finals
    0.06
    град
    0.06
    changing
    0.06
    _ROUTE
    0.06
    اى
    0.06
     maxY
    0.06
     Judy
    0.06
    Act Density 0.203%

    No Known Activations