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
    #@
    -0.07
    .Undef
    -0.07
    好看
    -0.06
    AdminController
    -0.06
     году
    -0.06
    لى
    -0.06
    =Value
    -0.06
    焘
    -0.06
    _trees
    -0.06
    :///
    -0.06
    POSITIVE LOGITS
    防腐
    0.06
     blat
    0.06
     proceso
    0.06
    antha
    0.06
    راق
    0.06
     aired
    0.06
    حظ
    0.06
     exemption
    0.06
    巧克力
    0.06
    PRESSION
    0.06
    Act Density 0.020%

    No Known Activations