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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    currentUser
    -0.07
    xito
    -0.07
    COMPARE
    -0.07
    Firstname
    -0.07
    partment
    -0.07
    LoggedIn
    -0.06
    ict
    -0.06
    Persona
    -0.06
     karış
    -0.06
     Currently
    -0.06
    POSITIVE LOGITS
    |m
    0.07
     LL
    0.07
    005
    0.07
    040
    0.06
    Ћ
    0.06
    _that
    0.06
     skl
    0.06
     Hed
    0.06
     Predicate
    0.06
     هست
    0.06
    Act Density 0.090%

    No Known Activations