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

    Neuronpedia

    INDEX
    Explanations

    issues related to attention, awareness, and communication, particularly in health and safety contexts

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

    warnings and detected issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.69
    expandindo
    -0.48
     مشين
    -0.43
    \{\\
    -0.40
     useAppContext
    -0.39
    WriteTagHelper
    -0.38
     göm
    -0.38
    Geografía
    -0.37
    
    -0.37
     Comprometido
    -0.36
    POSITIVE LOGITS
     indications
    0.63
     warnings
    0.60
     indication
    0.60
     signals
    0.58
     warning
    0.56
    Warnings
    0.54
     Indications
    0.53
     Warnings
    0.52
    signals
    0.51
    indications
    0.50
    Act Density 0.154%

    No Known Activations