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

    Neuronpedia

    INDEX
    Explanations

    biological classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remedy
    -0.08
     torment
    -0.07
     circumstances
    -0.07
    --)↵
    -0.07
    源源不断
    -0.06
    ッシ
    -0.06
    --}}↵
    -0.06
    од
    -0.06
     rel
    -0.06
     vex
    -0.06
    POSITIVE LOGITS
     alpha
    0.07
    %^
    0.07
    xsd
    0.07
    shared
    0.07
    hair
    0.06
    촬
    0.06
    FFFFFFFF
    0.06
     Zambia
    0.06
    obili
    0.06
    shots
    0.06
    Act Density 0.008%

    No Known Activations