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

    Neuronpedia

    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Never
    -0.07
     independent
    -0.07
     Chair
    -0.07
     визнача
    -0.07
    Fully
    -0.07
     제품
    -0.07
    Я
    -0.06
     triple
    -0.06
    Never
    -0.06
     leverage
    -0.06
    POSITIVE LOGITS
     detainees
    0.07
     nộp
    0.06
    _hop
    0.06
    auc
    0.06
    iteur
    0.06
    edata
    0.06
    pth
    0.06
     nông
    0.06
    deen
    0.06
     Pain
    0.06
    Act Density 0.083%

    No Known Activations