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

    Neuronpedia

    INDEX
    Explanations

    semantic equivalence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     있을
    0.44
    assembling
    0.43
    ियां
    0.39
    ιασ
    0.39
    ﭜ
    0.39
    ิค
    0.38
    ienten
    0.38
     colomb
    0.38
    uksia
    0.38
     verschiedenen
    0.38
    POSITIVE LOGITS
     of
    0.47
     Clown
    0.42
     Podcasts
    0.41
     الإنسان
    0.41
    CA
    0.40
     define
    0.40
    १९
    0.40
     Emerg
    0.40
    ูน
    0.39
    Ошибка
    0.39
    Act Density 0.003%

    No Known Activations