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
     Reject
    -0.07
    isOk
    -0.07
    ierte
    -0.06
     Highlight
    -0.06
    Trans
    -0.06
    ournaments
    -0.06
    nection
    -0.06
    Area
    -0.06
     собой
    -0.06
    ぶ
    -0.06
    POSITIVE LOGITS
     unrecognized
    0.06
     membranes
    0.06
     boj
    0.06
    탕
    0.06
    _longitude
    0.06
    Ком
    0.06
     nhiễm
    0.06
     Crosby
    0.06
     tempered
    0.06
    metic
    0.05
    Act Density 0.069%

    No Known Activations