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

    Neuronpedia

    INDEX
    Explanations

    roleplaying and acting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     butterfly
    -0.08
    已经
    -0.07
    ンジ
    -0.07
    ，则
    -0.07
     liter
    -0.06
     seating
    -0.06
    Verification
    -0.06
    ERİ
    -0.06
     �
    -0.06
     ihren
    -0.06
    POSITIVE LOGITS
    *);↵↵
    0.07
     #↵↵
    0.07
     Mississippi
    0.07
    .RequestBody
    0.06
    β
    0.06
    -window
    0.06
    constructor
    0.06
    0
    0.06
    ps
    0.06
    _font
    0.06
    Act Density 0.034%

    No Known Activations