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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simulation
    -0.08
    -energy
    -0.07
     ballot
    -0.07
     Lauderdale
    -0.07
    üss
    -0.07
    ,F
    -0.07
    SF
    -0.07
     shade
    -0.07
    "]).
    -0.06
     rotational
    -0.06
    POSITIVE LOGITS
     methodName
    0.06
     徒
    0.06
     entren
    0.06
    یزات
    0.06
     kesin
    0.06
    점
    0.06
    _STMT
    0.06
    /testify
    0.06
     dễ
    0.06
    linkedin
    0.06
    Act Density 0.068%

    No Known Activations