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

    Neuronpedia

    INDEX
    Explanations

    political accusations and threats

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

    accusations, threats, or pledges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NamedQueries
    -0.58
    kmäler
    -0.52
    AutoScaleMode
    -0.51
    ⤹
    -0.50
     kasarigan
    -0.50
     للاسماء
    -0.50
     AssemblyCulture
    -0.49
    enumii
    -0.49
    ExtendWith
    -0.49
     חיצוניים
    -0.48
    POSITIVE LOGITS
    offsetof
    0.42
     mis
    0.39
    empuan
    0.35
     Identify
    0.35
    StringLiteral
    0.34
     casual
    0.34
    つもり
    0.34
     stat
    0.33
    strom
    0.32
    ('--
    0.32
    Act Density 0.122%

    No Known Activations