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

    Neuronpedia

    INDEX
    Explanations

    bracketed code structures or syntax patterns in programming code

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

    error handling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.77
     Taktlose
    -0.63
     Conſ
    -0.61
     Signalez
    -0.59
     Reſ
    -0.58
    EndProject
    -0.58
    GEBURTSDATUM
    -0.55
    UserScript
    -0.55
    AsUp
    -0.54
    PerformLayout
    -0.53
    POSITIVE LOGITS
     Störungen
    0.41
     arşivlendi
    0.41
    éndole
    0.40
     errores
    0.39
    printStackTrace
    0.39
     sufrir
    0.37
    hawatir
    0.36
     herida
    0.36
     błę
    0.35
    instancetype
    0.35
    Act Density 0.007%

    No Known Activations