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

    Neuronpedia

    INDEX
    Explanations

    technology and data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Later
    0.59
     Anytime
    0.59
     TT
    0.58
     fore
    0.57
    シス
    0.57
     ters
    0.57
     Hub
    0.56
     ars
    0.56
     CLEAR
    0.56
     WP
    0.55
    POSITIVE LOGITS
    雍
    0.61
     народов
    0.61
    Symptoms
    0.59
     actuelle
    0.59
     andDevice
    0.59
    akyat
    0.59
    Pessoal
    0.58
     chaleur
    0.57
     vaisseaux
    0.57
    Immutable
    0.57
    Act Density 0.000%

    No Known Activations