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

    Neuronpedia

    INDEX
    Explanations

    , this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     метод
    0.49
    ibr
    0.47
     Metode
    0.45
    ral
    0.43
     Prom
    0.43
    iment
    0.42
     method
    0.41
     Method
    0.41
     कर्म
    0.41
     avenue
    0.41
    POSITIVE LOGITS
    lN
    0.42
    Capp
    0.41
    Carlton
    0.41
    ]]$
    0.40
     pejabat
    0.40
     खेलकर
    0.40
    WebKit
    0.40
    ځ
    0.40
    Murder
    0.40
    Animating
    0.39
    Act Density 0.000%

    No Known Activations