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

    Neuronpedia

    INDEX
    Explanations

    there is/are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ные
    0.54
    これで
    0.51
     resorption
    0.49
     humane
    0.46
     transitive
    0.46
    さて
    0.45
     banco
    0.44
     usable
    0.44
     daya
    0.43
     discrete
    0.43
    POSITIVE LOGITS
    л
    0.61
    ت
    0.59
    ਵ
    0.56
    abouts
    0.54
    jf
    0.53
    kou
    0.53
    atividade
    0.53
    েন
    0.52
    rops
    0.51
    zinha
    0.49
    Act Density 0.319%

    No Known Activations