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

    Neuronpedia

    INDEX
    Explanations

    application components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aunque
    1.05
    सँग
    0.99
     junit
    0.99
     servlet
    0.98
    лянчук
    0.98
    гене
    0.96
     azúcar
    0.96
     buildTypes
    0.95
     húmed
    0.95
     quark
    0.95
    POSITIVE LOGITS
    B
    0.87
    Anglo
    0.86
     B
    0.85
     Anglo
    0.84
    S
    0.83
    H
    0.83
    O
    0.82
    Repository
    0.78
    Y
    0.78
    F
    0.77
    Act Density 0.011%

    No Known Activations