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

    Neuronpedia

    INDEX
    Explanations

    "I" followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     garments
    0.35
     authentication
    0.33
     concatenation
    0.33
     ornamentation
    0.33
     cryptographic
    0.32
     restraints
    0.32
     assertions
    0.32
     conveyance
    0.32
     coverings
    0.32
    を使用
    0.31
    POSITIVE LOGITS
    ri
    0.33
     Бушлай
    0.32
    ida
    0.31
    zelf
    0.30
    ı
    0.30
    can
    0.30
     prawie
    0.29
    lo
    0.29
    conoc
    0.29
    zzet
    0.29
    Act Density 0.472%

    No Known Activations