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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of non-fulfillment

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

    if (! condition)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.89
    PerformLayout
    -0.82
    ⟬
    -0.72
    RenderAtEndOf
    -0.72
     pleaſure
    -0.69
    ſelf
    -0.68
     itſelf
    -0.65
     HttpNotFound
    -0.65
    majánló
    -0.65
    wapV
    -0.65
    POSITIVE LOGITS
     (!
    1.04
    (!
    0.93
     (!_
    0.73
    (!__
    0.68
     (!$
    0.68
     !
    0.67
    (!_
    0.66
    (!$
    0.65
     ((!
    0.60
    assertFalse
    0.57
    Act Density 0.007%

    No Known Activations