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

    Neuronpedia

    INDEX
    Explanations

    conventional understandings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swallowed
    0.44
    жаться
    0.44
    ensions
    0.40
    cartoon
    0.38
    Jdk
    0.38
     Elaina
    0.37
    presentable
    0.37
    习近平
    0.37
    iformes
    0.37
    రిత్ర
    0.36
    POSITIVE LOGITS
     Hoy
    0.43
     ស
    0.40
    Hoy
    0.39
     hoy
    0.39
     Marcell
    0.38
     puriso
    0.35
     Eros
    0.35
     अं
    0.35
     WATTS
    0.35
     δυνα
    0.34
    Act Density 0.000%

    No Known Activations