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

    Neuronpedia

    INDEX
    Explanations

    ing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സമൂഹ
    0.49
     robotics
    0.45
     గేమ్
    0.44
     Fácil
    0.43
    ണ്ട
    0.43
     batterie
    0.43
     degrés
    0.42
     lcd
    0.42
     Brady
    0.42
     pet
    0.41
    POSITIVE LOGITS
    Cert
    0.41
    ያስ
    0.41
     Cr
    0.38
     ζ
    0.38
    Include
    0.38
    Certificate
    0.38
     Admittedly
    0.37
    Watch
    0.37
    InputStream
    0.37
    Dal
    0.37
    Act Density 0.000%

    No Known Activations