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

    Neuronpedia

    INDEX
    Explanations

    patterns related to error messages and debugging information

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

    code file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.63
    ArgsConstructor
    -0.61
    Pyx
    -0.59
     يتيمه
    -0.58
     kaarangay
    -0.58
    dafx
    -0.58
    exitRule
    -0.57
    ambién
    -0.57
     '\\;'
    -0.55
     jadx
    -0.54
    POSITIVE LOGITS
     incident
    0.40
    Buongiorno
    0.40
     client
    0.37
     eventdata
    0.36
     klien
    0.34
    >{@
    0.34
     Client
    0.34
    incident
    0.33
    trooper
    0.33
     Incident
    0.33
    Act Density 0.406%

    No Known Activations