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

    Neuronpedia

    INDEX
    Explanations

    don't worry about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enl
    0.46
     hört
    0.45
    லாத
    0.43
    alq
    0.42
    रेख
    0.42
    ITwitter
    0.41
    alers
    0.40
    近い
    0.40
     различни
    0.40
     있고요
    0.40
    POSITIVE LOGITS
     eneste
    0.40
    ôle
    0.39
     entitlement
    0.39
    ()
    0.39
     Uma
    0.38
     paiement
    0.38
     disclosure
    0.38
    اں
    0.38
     valuation
    0.38
     insured
    0.37
    Act Density 0.000%

    No Known Activations