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

    Neuronpedia

    INDEX
    Explanations

    log in to accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Authentication
    0.47
    Authentication
    0.46
    認証
    0.45
    registration
    0.44
     authentication
    0.43
     регистра
    0.42
     auth
    0.42
    の中で
    0.42
     entries
    0.41
     inward
    0.41
    POSITIVE LOGITS
    ्तर
    0.45
    gend
    0.44
     dich
    0.44
    arranty
    0.44
     Pergamon
    0.40
    )|$(
    0.39
     Norge
    0.39
    ufen
    0.38
    GLAND
    0.38
    arkhand
    0.38
    Act Density 0.005%

    No Known Activations