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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens containing a double hyphen (e.g. BEM‐style CSS modifiers like “--large”, “--medium”, “--small”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MJ
    -0.07
     있
    -0.07
     مخ
    -0.07
    (Program
    -0.07
     Syntax
    -0.07
    わず
    -0.07
    MimeType
    -0.06
     GPU
    -0.06
    墓
    -0.06
    Strength
    -0.06
    POSITIVE LOGITS
     LIMIT
    0.07
    phasis
    0.06
    işleri
    0.06
    achelor
    0.06
     ode
    0.06
    -Allow
    0.06
     ail
    0.06
    .conn
    0.06
     Liebe
    0.06
    شنامه
    0.06
    Act Density 0.132%

    No Known Activations