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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to sections or steps in instructional texts

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geſch
    -0.92
     beſch
    -0.91
     ſei
    -0.90
    niſſe
    -0.89
     ſeine
    -0.86
     imagui
    -0.85
    ſicht
    -0.85
     erſt
    -0.84
     verſch
    -0.84
     ſind
    -0.84
    POSITIVE LOGITS
    ,
    0.45
    .
    0.36
    z
    0.35
    The
    0.32
    W
    0.31
    :
    0.31
     subsequently
    0.31
    ta
    0.30
    providedIn
    0.28
    L
    0.28
    Act Density 0.074%

    No Known Activations