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

    Neuronpedia

    INDEX
    Explanations

    Code, technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Тип
    -0.07
     מ
    -0.06
    ắc
    -0.06
    -Sah
    -0.06
     Bukkit
    -0.06
     Billion
    -0.06
    .And
    -0.06
    .large
    -0.06
     browse
    -0.06
     verv
    -0.06
    POSITIVE LOGITS
     Destroy
    0.07
    озна
    0.06
    Artifact
    0.06
    Flat
    0.06
     Ada
    0.06
    _RIGHT
    0.06
    OLD
    0.06
    Write
    0.06
     механи
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations