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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and how messages are conveyed

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

    execution, delivery or presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ToBounds
    -0.37
    enumii
    -0.35
     asistente
    -0.33
     tvor
    -0.33
     gadis
    -0.31
     مُعرِّف
    -0.31
     görüntü
    -0.30
    ัณฑ
    -0.30
    Sommaire
    -0.29
     purposes
    -0.29
    POSITIVE LOGITS
     <>",
    0.60
    ⟬
    0.59
     CURIAM
    0.58
    ########.
    0.57
    HideFlags
    0.57
    ⤹
    0.52
    ModelAdmin
    0.51
     OCH
    0.48
    anyahu
    0.48
    manera
    0.47
    Act Density 0.085%

    No Known Activations