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

    Neuronpedia

    INDEX
    Explanations

    combat encounters and defeating enemies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    842
    -0.07
    	Point
    -0.07
     mortar
    -0.06
     darkest
    -0.06
    �
    -0.06
     remar
    -0.06
     knowing
    -0.06
     wrist
    -0.06
     categoryId
    -0.06
     surprises
    -0.06
    POSITIVE LOGITS
     ExecutionContext
    0.07
     Halk
    0.06
     Δή
    0.06
    _package
    0.06
     hamburger
    0.06
    一緒
    0.06
    .ext
    0.06
    .toLowerCase
    0.06
    /plain
    0.06
     Εκ
    0.06
    Act Density 0.041%

    No Known Activations