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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    병
    -0.07
     Cooke
    -0.07
    categories
    -0.06
    _tuples
    -0.06
    year
    -0.06
    кая
    -0.06
     dado
    -0.06
    _RIGHT
    -0.06
     Notes
    -0.06
     Original
    -0.06
    POSITIVE LOGITS
    cps
    0.07
     Dynamo
    0.07
    ≦
    0.07
    EU
    0.06
    NK
    0.06
    秒
    0.06
     レ
    0.06
    lam
    0.06
    gota
    0.06
    /li
    0.06
    Act Density 0.101%

    No Known Activations