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

    Neuronpedia

    INDEX
    Explanations

    structural elements and layout properties in code

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

    UI layout attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reaſon
    -0.45
     habet
    -0.42
     cauſe
    -0.41
     poffible
    -0.40
     secundario
    -0.40
     pleaſure
    -0.40
    ModelForm
    -0.39
     ddelweddau
    -0.39
     houſe
    -0.38
     quoque
    -0.38
    POSITIVE LOGITS
    Autoritní
    0.65
    存于互联网档案馆
    0.60
    olingo
    0.53
    foria
    0.52
     autorytatywna
    0.51
     Robo
    0.50
     Kimmel
    0.50
    expandindo
    0.50
    setti
    0.50
    utsu
    0.49
    Act Density 0.011%

    No Known Activations