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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     randomized
    -0.07
    184
    -0.07
    (lang
    -0.06
     communities
    -0.06
    modal
    -0.06
     hills
    -0.06
     ErrorCode
    -0.06
    495
    -0.06
    practice
    -0.06
    329
    -0.06
    POSITIVE LOGITS
     الآ
    0.06
    FormData
    0.06
    _S
    0.06
    нер
    0.06
    xFB
    0.06
     ausge
    0.06
    _EM
    0.06
     Волод
    0.06
    .BAD
    0.06
    }";↵↵
    0.06
    Act Density 0.197%

    No Known Activations