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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

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

    closing resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.57
     ſche
    -0.54
     Jefus
    -0.54
     avoient
    -0.53
     Majefty
    -0.51
    offsetof
    -0.50
     étoient
    -0.48
    الحياه
    -0.47
     myſelf
    -0.46
    TargetException
    -0.44
    POSITIVE LOGITS
    SOUNDBITE
    0.44
     InputDecoration
    0.43
    Билгалдахарш
    0.42
     pymysql
    0.40
     nakalista
    0.39
    WithMany
    0.36
    archiviato
    0.35
     phased
    0.35
    大利
    0.34
     reset
    0.33
    Act Density 0.005%

    No Known Activations