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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and references to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text following certain punctuation or formatting

    np_acts-logits-general · gemini-2.0-flash

    of followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _$
    -0.60
     "
    -0.59
     '
    -0.57
     App
    -0.55
     um
    -0.53
     ‘
    -0.51
     _
    -0.51
    Leftrightarrow
    -0.51
     app
    -0.50
     doble
    -0.49
    POSITIVE LOGITS
     Majefty
    1.02
     Houſe
    1.01
     itſelf
    0.99
     myſelf
    0.97
    ſelves
    0.94
    ſelf
    0.91
     themſelves
    0.90
     Chriftian
    0.87
     Jefus
    0.86
     uſe
    0.85
    Act Density 0.729%

    No Known Activations