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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     此
    -0.06
     implemented
    -0.06
    婦
    -0.06
    tein
    -0.06
    _SPECIAL
    -0.06
    idges
    -0.06
     smoothly
    -0.06
    لیسی
    -0.06
    ählt
    -0.06
    状況
    -0.06
    POSITIVE LOGITS
     donate
    0.07
    	override
    0.06
     Turner
    0.06
     sublic
    0.06
     predominantly
    0.06
     Smith
    0.06
    _toggle
    0.06
    nici
    0.06
     Pavel
    0.06
    .QRect
    0.06
    Act Density 0.055%

    No Known Activations