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

    Neuronpedia

    INDEX
    Explanations

    abstract fundamental concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     socio
    0.29
     ihrer
    0.29
     számos
    0.28
     `<
    0.27
     camb
    0.26
     antioxidant
    0.26
     jų
    0.25
     mutagen
    0.25
     DREAM
    0.25
     apoptotic
    0.25
    POSITIVE LOGITS
     itself
    0.60
    本身
    0.52
    本身的
    0.43
     자체
    0.39
    fulness
    0.35
    lessness
    0.33
     вообще
    0.32
    uous
    0.32
    和
    0.32
    ful
    0.31
    Act Density 0.101%

    No Known Activations