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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mrs
    -0.08
    орган
    -0.07
    iner
    -0.07
     Org
    -0.07
    érons
    -0.07
    bly
    -0.07
    -0.07
    ero
    -0.07
    ternal
    -0.07
    Attached
    -0.07
    POSITIVE LOGITS
     என்பதை
    0.11
     என்ற
    0.10
     అనే
    0.10
     என்று
    0.09
     అని
    0.09
     என்ப
    0.09
     എന്ന്
    0.09
     を
    0.09
     இல்லை
    0.09
     desigual
    0.09
    Act Density 0.031%
    No Known Activations