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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal violations and abuses of rights

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

    legal violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEX
    -0.49
    roppo
    -0.45
    ulgação
    -0.42
    lgari
    -0.41
    Tikang
    -0.41
    hower
    -0.40
    illips
    -0.40
    diğinde
    -0.39
     Synthesis
    -0.39
     passively
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    0.59
    VersionUID
    0.45
     IActionResult
    0.43
    IActionResult
    0.42
    XmlAccessType
    0.41
     act
    0.41
    Tembelea
    0.41
    Varint
    0.40
    printStackTrace
    0.40
     crime
    0.40
    Act Density 0.067%

    No Known Activations