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

    Neuronpedia

    INDEX
    Explanations

    explanations and reasoning in personal or subjective reflections

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

    speculative explanations or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.75
     estekak
    -0.58
    PerformLayout
    -0.49
    StoryboardSegue
    -0.48
     recevrez
    -0.48
    Manbalar
    -0.47
    anthene
    -0.46
     للمعارف
    -0.45
    AddTagHelper
    -0.45
    enumii
    -0.45
    POSITIVE LOGITS
     maybe
    0.59
    それとも
    0.57
     or
    0.54
     Maybe
    0.53
    Maybe
    0.52
    maybe
    0.51
     perhaps
    0.50
     Perhaps
    0.47
    Perhaps
    0.47
    ?).
    0.47
    Act Density 0.103%

    No Known Activations