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

    Neuronpedia

    INDEX
    Explanations

    about tabla

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istani
    0.42
     tant
    0.40
    ल्पनिक
    0.39
     Lank
    0.38
     Abram
    0.38
     liberdade
    0.38
     Ste
    0.37
    ில்லிய
    0.37
    섞
    0.37
     Barge
    0.36
    POSITIVE LOGITS
    osov
    0.47
    Diffusion
    0.42
    osso
    0.40
    pyrimidine
    0.40
    冷
    0.40
     Diffusion
    0.39
    тала
    0.38
     frag
    0.38
    Blood
    0.38
     diffusion
    0.37
    Act Density 0.000%

    No Known Activations