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

    Neuronpedia

    INDEX
    Explanations

    automatically create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tenha
    0.48
     TBR
    0.48
     retreated
    0.46
     камен
    0.45
    懷
    0.45
    ية
    0.44
    ҳа
    0.44
     Jangan
    0.44
    𒆷
    0.43
     cartão
    0.43
    POSITIVE LOGITS
    urk
    0.44
    FBSDKInternal
    0.44
    UKI
    0.43
    imhe
    0.43
    ur
    0.43
    specification
    0.43
     itertools
    0.41
     winnings
    0.41
     superconduct
    0.40
    👁
    0.40
    Act Density 0.000%

    No Known Activations