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

    Neuronpedia

    INDEX
    Explanations

    acceptance doesn't mean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eur
    1.18
    eurs
    1.15
    iere
    1.13
    m
    1.11
    anız
    1.08
     Faites
    1.08
     마련
    1.05
    ৃক
    1.04
    ir
    1.01
    nsk
    1.00
    POSITIVE LOGITS
     pierws
    1.30
     isIn
    1.27
    𝑺
    1.24
     tumbuhan
    1.12
     tilted
    1.12
     tuin
    1.12
    fileExists
    1.11
    𝙩
    1.10
    𝒔
    1.08
    Thrown
    1.07
    Act Density 0.001%

    No Known Activations