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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (program
    -0.06
     standby
    -0.06
    VARCHAR
    -0.06
    ertiary
    -0.06
    四
    -0.06
    Backing
    -0.06
     Wahl
    -0.06
    UInteger
    -0.06
     -----------
    -0.06
     Vanity
    -0.06
    POSITIVE LOGITS
     شرق
    0.08
    орі
    0.07
    /firebase
    0.07
     теат
    0.06
    часно
    0.06
    (())↵
    0.06
    createForm
    0.06
     infring
    0.06
    láš
    0.06
     이후
    0.06
    Act Density 0.003%

    No Known Activations