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

    Neuronpedia

    INDEX
    Explanations

    public class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marshal
    0.78
     bulge
    0.73
     Marshall
    0.73
    setAdapter
    0.71
    Param
    0.70
    लीकरण
    0.70
    Eras
    0.69
     Eras
    0.68
     Gerry
    0.68
     atrás
    0.68
    POSITIVE LOGITS
    rit
    0.64
    skaya
    0.61
    )['
    0.60
    皇家
    0.58
    unk
    0.58
    ber
    0.57
     aves
    0.57
    Rit
    0.56
    autonomous
    0.56
    alarına
    0.55
    Act Density 0.075%

    No Known Activations