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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and conditional phrases

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

    German conjunctions or sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.77
    ſelf
    -0.66
    featureID
    -0.65
     pleaſure
    -0.65
    RectangleBorder
    -0.62
     viewDidLoad
    -0.60
    -0.60
    ngrx
    -0.59
    rativa
    -0.59
    :✨
    -0.58
    POSITIVE LOGITS
     dass
    0.79
     terwijl
    0.63
    ewel
    0.59
     womit
    0.57
    Nachdem
    0.57
     nadat
    0.56
    wijl
    0.56
     waarmee
    0.54
     daß
    0.53
     nachdem
    0.52
    Act Density 0.015%

    No Known Activations