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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inability or restrictions

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

    Punctuation, especially quotes and commas

    np_acts-logits-general · gemini-2.0-flash

    timestamp seconds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.08
    PMailer
    -0.91
     utafitiHapana
    -0.88
    )”.
    -0.88
    +:+
    -0.82
    ”…
    -0.80
    RepeatedField
    -0.78
     يتيمه
    -0.77
    клопе
    -0.77
     comuniques
    -0.76
    POSITIVE LOGITS
    .
    0.58
     --
    0.48
    ,
    0.46
     chiam
    0.41
     —
    0.41
    setSubject
    0.40
    --
    0.40
     papá
    0.40
     Mm
    0.39
    —
    0.39
    Act Density 0.105%

    No Known Activations