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

    Neuronpedia

    INDEX
    Explanations

    aging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     му
    -0.07
     post
    -0.07
    person
    -0.07
     Thanksgiving
    -0.07
    worker
    -0.07
    categoria
    -0.06
     Fallon
    -0.06
     drills
    -0.06
     بلغ
    -0.06
     grandi
    -0.06
    POSITIVE LOGITS
    нав
    0.07
    울
    0.06
    usiness
    0.06
    _UNKNOWN
    0.06
    -print
    0.06
     nhiên
    0.06
     少
    0.06
     ApiException
    0.06
    獨
    0.06
    CLUD
    0.06
    Act Density 0.114%

    No Known Activations