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

    Neuronpedia

    INDEX
    Explanations

    why and because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    casa
    0.44
     tener
    0.43
    m
    0.42
    pada
    0.41
     animations
    0.41
     government
    0.41
     secret
    0.40
     enviar
    0.40
     ambienti
    0.40
     HDTV
    0.40
    POSITIVE LOGITS
     Synonym
    0.43
     继续
    0.42
    μεριν
    0.42
     Unknown
    0.41
    적인
    0.40
    0.40
    隰
    0.39
    ում
    0.38
     여러
    0.38
    ibility
    0.38
    Act Density 0.007%

    No Known Activations