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

    Neuronpedia

    INDEX
    Explanations

    issues related to legal proceedings and evidential practices

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

    Failure to act or disclose information

    np_acts-logits-general · gemini-2.0-flash

    failure to properly act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.87
    IsMutable
    -0.79
    istoitu
    -0.79
     Roskov
    -0.78
     समीक्षाएं
    -0.78
     autorytatywna
    -0.76
     myſelf
    -0.75
    setVerticalGroup
    -0.74
    StoryboardSegue
    -0.73
    ConstraintMaker
    -0.71
    POSITIVE LOGITS
     nor
    0.97
     properly
    0.96
     or
    0.87
     nici
    0.77
     nemmeno
    0.77
     anymore
    0.75
    properly
    0.72
    而是
    0.71
     adequately
    0.71
     proper
    0.70
    Act Density 0.605%

    No Known Activations