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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating characteristics or classifications of subjects

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

    characterized by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keuangan
    -0.48
     Houſe
    -0.45
     carav
    -0.44
     Investigaciones
    -0.44
     Komunikasi
    -0.44
     medicina
    -0.43
     Jefus
    -0.43
     presidencia
    -0.43
    Morte
    -0.43
     olimp
    -0.43
    POSITIVE LOGITS
     characterized
    0.74
    aktery
    0.71
     characterised
    0.61
    SharedCtor
    0.55
     distinctive
    0.53
     caratter
    0.52
     Marked
    0.51
    #![
    0.51
    nonatomic
    0.50
     характеризу
    0.50
    Act Density 0.021%

    No Known Activations