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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing desire or intent in the speaker

    oai_token-act-pair · gemini-2.0-flash

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oredCriteria
    -1.10
     itſelf
    -1.03
     Efq
    -1.02
    -0.96
     myſelf
    -0.93
     Monfieur
    -0.93
    featureID
    -0.91
     himſelf
    -0.88
    GEBURTSDATUM
    -0.85
     themſelves
    -0.84
    POSITIVE LOGITS
     for
    0.57
     a
    0.56
     an
    0.53
     neither
    0.52
     M
    0.50
     maioria
    0.49
     mostly
    0.49
    HORE
    0.49
     both
    0.49
     Tag
    0.49
    Act Density 1.956%

    No Known Activations