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

    Neuronpedia

    INDEX
    Explanations

    Code/log snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on subword pieces of CamelCase identifiers in code (e.g. parts of function or class names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exploration
    -0.07
     Authorization
    -0.06
    اده
    -0.06
     landmark
    -0.06
    Updates
    -0.06
     organizing
    -0.06
    .parent
    -0.06
    fieldset
    -0.06
    turnstile
    -0.06
    ケース
    -0.06
    POSITIVE LOGITS
    หา
    0.07
    Ada
    0.06
     dimin
    0.06
     overlays
    0.06
     Catalonia
    0.06
     můj
    0.06
    над
    0.06
    EXTERN
    0.06
    .JOptionPane
    0.06
    fluence
    0.06
    Act Density 0.029%

    No Known Activations