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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operation-related terms

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

    Severity, impact, consequences, or damages

    np_acts-logits-general · gemini-2.0-flash

    damage and negative consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reciate
    -0.56
    enoord
    -0.54
     rağmen
    -0.53
    InputTagHelper
    -0.53
    Optim
    -0.52
     Biôgrafia
    -0.52
    Успе
    -0.51
     miracle
    -0.51
     overjoyed
    -0.51
    ελ
    -0.50
    POSITIVE LOGITS
     severity
    1.06
     Severity
    0.86
     damaging
    0.84
     impacts
    0.83
     damage
    0.82
    severity
    0.80
     affecting
    0.79
     impact
    0.79
     consequences
    0.78
     damages
    0.77
    Act Density 1.116%

    No Known Activations