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

    Neuronpedia

    INDEX
    Explanations

    lists of concepts and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onus
    0.41
     oss
    0.39
     committed
    0.38
     Crac
    0.38
     people
    0.37
     cria
    0.36
     -->'
    0.36
     c
    0.36
     SA
    0.36
     crea
    0.35
    POSITIVE LOGITS
    특히
    0.57
     және
    0.55
     மற்றும்
    0.54
    。
    0.54
    especially
    0.52
    including
    0.51
    하면서
    0.49
     ਅਤੇ
    0.48
    😬
    0.47
     и
    0.46
    Act Density 0.101%

    No Known Activations