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

    Neuronpedia

    INDEX
    Explanations

    capital letters, likely indicating specific terms or acronyms

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

    reconstructions, strain, concentration, islands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.79
     desmotivaciones
    -0.63
     Vikipedi
    -0.63
     يتيمه
    -0.60
     fashiola
    -0.60
     صوتيه
    -0.57
    Jeografia
    -0.56
    expandindo
    -0.56
     للاسماء
    -0.56
    Tikang
    -0.56
    POSITIVE LOGITS
    dB
    0.50
    aS
    0.48
    nC
    0.47
    tC
    0.46
    ragamo
    0.44
    uD
    0.43
    iP
    0.43
    dS
    0.43
    makeText
    0.42
    WoW
    0.42
    Act Density 0.094%

    No Known Activations