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

    Neuronpedia

    INDEX
    Explanations

    discussing "the whole thing."

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pleeg
    -0.08
    tw
    -0.08
     Nordeste
    -0.08
    _tw
    -0.07
    तम
    -0.07
    тет
    -0.07
    ternal
    -0.07
     među
    -0.07
     Tw
    -0.07
     ned
    -0.07
    POSITIVE LOGITS
    整个
    0.11
     మొత్త
    0.11
     మొత్తం
    0.11
     cały
    0.09
     മുഴ
    0.09
     hele
    0.09
     seluruh
    0.09
     inteiro
    0.09
     inteira
    0.09
     تقريب
    0.09
    Act Density 0.051%

    No Known Activations