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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UNION
    0.80
    Decision
    0.80
     decisión
    0.78
    स्तू
    0.77
     decisione
    0.77
     판단
    0.76
     Decision
    0.75
     Decisions
    0.75
    Union
    0.74
     सलामी
    0.74
    POSITIVE LOGITS
     wading
    0.68
    வலை
    0.61
     meant
    0.60
    盗
    0.59
    ἆ
    0.59
    міну
    0.58
    दर्भ
    0.58
     Rivers
    0.58
     ओर
    0.58
     Brewer
    0.58
    Act Density 0.006%

    No Known Activations