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

    Neuronpedia

    INDEX
    Explanations

    language pairs, learn, AI messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     કરે
    0.48
    écran
    0.45
     obstáculos
    0.45
    发动机
    0.45
     conversación
    0.45
    ⒏
    0.44
     Supportive
    0.44
    론
    0.44
     연료
    0.44
     motocicleta
    0.44
    POSITIVE LOGITS
     derm
    0.48
     prof
    0.48
     profil
    0.47
     so
    0.46
     mime
    0.46
     pi
    0.45
     ECM
    0.44
     一般
    0.44
    ื
    0.43
     Pi
    0.43
    Act Density 0.004%

    No Known Activations