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

    Neuronpedia

    INDEX
    Explanations

    slashes and hyphens in web links

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

    URLs followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    website links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -1.21
     I
    -0.95
    .
    -0.94
     der
    -0.93
     di
    -0.93
    :
    -0.92
     D
    -0.91
     sa
    -0.90
     la
    -0.90
     S
    -0.90
    POSITIVE LOGITS
     itſelf
    1.91
     Houſe
    1.80
     Majefty
    1.78
     Reſ
    1.70
     Diſ
    1.65
     Efq
    1.64
     Anſ
    1.59
     Jefus
    1.56
     Monfieur
    1.54
     Perſ
    1.54
    Act Density 0.483%

    No Known Activations