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

    Neuronpedia

    INDEX
    Explanations

    code/logs/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /view
    -0.07
    عف
    -0.07
    IENT
    -0.06
    committed
    -0.06
    nier
    -0.06
    Workspace
    -0.06
    razil
    -0.06
     Experiment
    -0.06
    840
    -0.06
    letion
    -0.06
    POSITIVE LOGITS
    .flatMap
    0.07
     Whoever
    0.07
    enumerator
    0.07
     この
    0.07
    _prog
    0.06
     announc
    0.06
    参加
    0.06
     قانون
    0.06
    essage
    0.06
     висок
    0.06
    Act Density 0.000%

    No Known Activations