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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers, particularly timestamps or file versions

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

    numerical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.41
    Personendaten
    -0.32
     cuero
    -0.30
     ویکی‌پدیای
    -0.28
     assister
    -0.28
     empleado
    -0.28
     actuelles
    -0.28
    voorbeeld
    -0.28
     acompañado
    -0.27
     further
    -0.27
    POSITIVE LOGITS
    UserScript
    0.69
    StructEnd
    0.66
    :✨
    0.66
     defaultstate
    0.60
    RTEE
    0.58
     gynhyrchwyd
    0.55
    期刊论文
    0.55
     nonUne
    0.55
    0.54
    Peters
    0.53
    Act Density 0.007%

    No Known Activations