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

    Neuronpedia

    INDEX
    Explanations

    place where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     है
    0.52
     моего
    0.52
     bisschen
    0.49
     정말
    0.48
    really
    0.48
     REALLY
    0.48
     really
    0.47
     increí
    0.46
    𝖽
    0.45
     मेरी
    0.45
    POSITIVE LOGITS
     voidaan
    0.64
     researchers
    0.63
     each
    0.56
     patients
    0.56
     designers
    0.55
     motorists
    0.55
     certain
    0.54
     during
    0.54
     individuals
    0.54
     participants
    0.53
    Act Density 0.058%

    No Known Activations