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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Medium
    -0.07
     Leigh
    -0.07
     Dar
    -0.06
    calar
    -0.06
     Attempt
    -0.06
     plummet
    -0.06
     的
    -0.06
     افت
    -0.06
    ponents
    -0.06
     Transformation
    -0.06
    POSITIVE LOGITS
     "-"↵
    0.07
    +m
    0.07
    Falsy
    0.06
     {[
    0.06
    .Identifier
    0.06
    .Application
    0.06
    ="",
    0.06
    .setForeground
    0.06
    ัดส
    0.06
    _()↵
    0.06
    Act Density 0.003%

    No Known Activations