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

    Neuronpedia

    INDEX
    Explanations

    Hyderabad, CoQ10, Hazards, rabies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    than
    0.62
    ge
    0.59
    Than
    0.54
    an
    0.53
    G
    0.52
    pkins
    0.50
    A
    0.49
    Ord
    0.48
     än
    0.48
    Raj
    0.46
    POSITIVE LOGITS
     dieci
    0.55
     voici
    0.55
     ၁
    0.54
     Middleware
    0.53
     reflexive
    0.52
     conosco
    0.50
     titoli
    0.49
    t
    0.49
     Housewives
    0.49
     Yii
    0.49
    Act Density 0.000%

    No Known Activations