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

    Neuronpedia

    INDEX
    Explanations

    Punctuation or sentence separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ObjectMapper
    -0.08
     real
    -0.07
     professions
    -0.07
     corrosion
    -0.07
     nutrition
    -0.07
    ark
    -0.06
    lw
    -0.06
    cial
    -0.06
    ��
    -0.06
     kteří
    -0.06
    POSITIVE LOGITS
    ü
    0.06
    retweeted
    0.06
    ')
↵
↵
    0.06
    .Dropout
    0.06
    /process
    0.06
    quoise
    0.06
     ""),↵
    0.06
    [--
    0.06
    _feedback
    0.06
     exem
    0.06
    Act Density 0.132%

    No Known Activations