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

    Neuronpedia

    INDEX
    Explanations

    educational requirements

    oai_token-act-pair · gemini-2.0-flash

    academic/scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.73
     myſelf
    -0.69
     Bourgoin
    -0.68
     Wikimedijinoj
    -0.65
     itſelf
    -0.65
     تضيفلها
    -0.60
     Jefus
    -0.59
    ſelves
    -0.57
     whoſe
    -0.57
     uſe
    -0.56
    POSITIVE LOGITS
     tiế
    0.48
    zado
    0.48
     Grimes
    0.47
    zan
    0.45
    UN
    0.45
    øj
    0.44
    spreis
    0.44
     Straus
    0.44
    θρω
    0.44
    py
    0.43
    Act Density 0.689%

    No Known Activations