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

    Neuronpedia

    INDEX
    Explanations

    copyright statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.63
    oretically
    1.63
    是非常
    1.52
     POINTS
    1.49
    ו
    1.49
    ﻛ
    1.45
    ERSHIP
    1.42
     cí
    1.41
     faptul
    1.41
    avier
    1.31
    POSITIVE LOGITS
    €“
    1.64
    re
    1.55
    PhysRev
    1.48
    ė
    1.48
    ли
    1.47
    ्डा
    1.45
    toluene
    1.45
    х
    1.45
    ת
    1.45
     einen
    1.43
    Act Density 0.004%

    No Known Activations