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

    Neuronpedia

    INDEX
    Explanations

    code roles and interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.65
    ો
    1.64
    s
    1.56
    ON
    1.51
    V
    1.44
    angry
    1.41
    runs
    1.41
    sal
    1.39
    ay
    1.38
    ang
    1.38
    POSITIVE LOGITS
     Rho
    1.24
     Ты
    1.23
     Такие
    1.21
     satisfactorily
    1.20
     Trời
    1.20
     anxiously
    1.19
    िश्वत
    1.19
     Pengh
    1.17
     Equest
    1.16
     Southerners
    1.16
    Act Density 0.004%

    No Known Activations