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

    Neuronpedia

    INDEX
    Explanations

    OP followed by technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auss
    0.40
     zust
    0.39
    arga
    0.39
    erk
    0.39
     സേ
    0.38
     Jess
    0.38
    PHONY
    0.38
    vedad
    0.38
    ffekt
    0.38
    quale
    0.37
    POSITIVE LOGITS
     ocul
    0.40
     externally
    0.39
     हृदय
    0.38
     wides
    0.37
     coppia
    0.37
    ວ
    0.37
     resolução
    0.37
     तैर
    0.37
    HIB
    0.37
    ------+
    0.37
    Act Density 0.004%

    No Known Activations