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

    Neuronpedia

    INDEX
    Explanations

    code-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -------------------------------------------------------------------------↵
    -0.07
     Ecc
    -0.07
     така
    -0.06
    -NLS
    -0.06
     stif
    -0.06
    operator
    -0.06
     includ
    -0.06
     unpublished
    -0.06
    ?";↵
    -0.06
     '"'
    -0.06
    POSITIVE LOGITS
    アル
    0.07
     Essen
    0.07
    기
    0.06
    macen
    0.06
     Tucker
    0.06
     слов
    0.06
    levant
    0.06
     Agents
    0.06
    stable
    0.06
    实验
    0.06
    Act Density 0.000%

    No Known Activations