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

    Neuronpedia

    INDEX
    Explanations

    feel for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stesse
    0.63
    ul
    0.55
     perdu
    0.54
    es
    0.54
    }{\
    0.53
    indicator
    0.53
    a
    0.53
    empres
    0.53
    ing
    0.52
     tercer
    0.51
    POSITIVE LOGITS
    لى
    0.49
     polymorphism
    0.47
    ञ
    0.45
     seo
    0.43
     validity
    0.42
    перыі
    0.42
     potency
    0.42
    闿
    0.41
    ।'
    0.40
     emf
    0.40
    Act Density 0.001%

    No Known Activations