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

    Neuronpedia

    INDEX
    Explanations

    dependency versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excav
    0.46
     kartu
    0.44
    Cock
    0.44
     invade
    0.44
    7
    0.44
     छापे
    0.44
     στην
    0.43
     infotainment
    0.43
    the
    0.42
     presso
    0.42
    POSITIVE LOGITS
    !।
    0.47
     기다
    0.44
    ли
    0.43
    గి
    0.42
     đợi
    0.41
    wdir
    0.40
    ም።
    0.40
    ừng
    0.39
     年
    0.38
     Như
    0.38
    Act Density 0.004%

    No Known Activations