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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	md
    -0.07
    -heavy
    -0.07
    痃
    -0.07
     \%
    -0.06
     deficits
    -0.06
    凄
    -0.06
    憧
    -0.06
     הנוכ
    -0.06
    孤
    -0.06
     '..',
    -0.06
    POSITIVE LOGITS
    باح
    0.07
     wrapping
    0.07
    옭
    0.07
    这是
    0.06
    ATION
    0.06
    _edit
    0.06
    because
    0.06
    위원장
    0.06
     plumbing
    0.06
    阴谋
    0.06
    Act Density 0.096%

    No Known Activations