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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -history
    -0.06
     حق
    -0.06
    <number
    -0.06
    NUMBER
    -0.06
     spectacle
    -0.05
    _MEM
    -0.05
    _TREE
    -0.05
    _movement
    -0.05
    İTESİ
    -0.05
     website
    -0.05
    POSITIVE LOGITS
    ',{↵
    0.08
    、“
    0.07
    -contrib
    0.07
     Lux
    0.06
     увид
    0.06
     Immediate
    0.06
    rid
    0.06
    ξε
    0.06
    」，
    0.06
    vious
    0.06
    Act Density 0.026%

    No Known Activations