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

    Neuronpedia

    INDEX
    Explanations

    coming soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻀ
    0.42
    TryParse
    0.37
    ент
    0.36
    митри
    0.36
     verstehen
    0.35
    specificity
    0.35
    бор
    0.34
    ousand
    0.34
    hadap
    0.34
    DomainMask
    0.34
    POSITIVE LOGITS
     Coming
    1.47
     coming
    1.41
    Coming
    1.40
     forthcoming
    1.38
    COMING
    1.35
    coming
    1.32
     soon
    1.30
    soon
    1.16
     bientôt
    1.12
     Soon
    1.09
    Act Density 0.005%

    No Known Activations