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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that resemble file or variable names

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

    Hexadecimal strings/identifiers

    np_acts-logits-general · gemini-2.0-flash

    hex sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.77
    erialize
    -0.72
    rettes
    -0.70
    ″]
    -0.70
    GraphicsUnit
    -0.70
    atelli
    -0.67
    ]]
    -0.66
    METRO
    -0.64
    发表于
    -0.64
    oader
    -0.63
    POSITIVE LOGITS
     ejus
    0.67
     nicio
    0.63
    </thead>
    0.63
     ISNI
    0.61
     fusca
    0.60
     varandra
    0.60
     eût
    0.58
     feroit
    0.58
     coscienza
    0.57
     auroit
    0.57
    Act Density 0.089%

    No Known Activations