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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SER
    -0.07
     jer
    -0.07
     spawned
    -0.07
    "He
    -0.06
     canceled
    -0.06
    /community
    -0.06
     elegant
    -0.06
     num
    -0.06
    ॉड
    -0.06
    —they
    -0.06
    POSITIVE LOGITS
     komple
    0.07
    せ
    0.06
    ㆍ
    0.06
     iii
    0.06
    ensex
    0.06
    073
    0.06
     Tài
    0.06
    고
    0.06
    ằm
    0.06
     şöyle
    0.06
    Act Density 0.192%

    No Known Activations