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

    Neuronpedia

    INDEX
    Explanations

    control or power dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ﺍﻟ
    0.54
    '"
    0.52
    IoT
    0.52
    IOT
    0.51
    Indianapolis
    0.50
    ONS
    0.50
    AKE
    0.48
    ENT
    0.46
    ﺮ
    0.45
    OCKET
    0.45
    POSITIVE LOGITS
     biochemical
    0.47
     ubiquitin
    0.47
     aclarar
    0.47
     hypothesized
    0.46
     spannend
    0.46
     iā
    0.45
     Medica
    0.44
     computational
    0.43
     Computational
    0.43
     Biochemical
    0.43
    Act Density 0.001%

    No Known Activations