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

    Neuronpedia

    INDEX
    Explanations

    planned Ukraine; Velocity amplify physical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     republic
    0.49
     spun
    0.48
     precedent
    0.48
     Miro
    0.46
     DeConcini
    0.46
     A
    0.45
     consumer
    0.45
     Wilcox
    0.45
     swam
    0.45
     caseload
    0.45
    POSITIVE LOGITS
    gebras
    0.48
    OfYear
    0.47
    epochs
    0.45
     sobra
    0.45
    damping
    0.44
    Renew
    0.44
    phalodes
    0.44
    naeus
    0.43
    Anime
    0.42
    kf
    0.41
    Act Density 0.030%

    No Known Activations