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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Validation
    -0.07
     množ
    -0.07
    .dropdown
    -0.07
    .ToolStripSeparator
    -0.07
     moyen
    -0.06
    žít
    -0.06
    autom
    -0.06
     Bugün
    -0.06
    ें।
    -0.06
     sextreffen
    -0.06
    POSITIVE LOGITS
     гар
    0.07
    獲
    0.07
    -aff
    0.07
    +=
    0.06
     refin
    0.06
    \Domain
    0.06
    ufact
    0.06
     шах
    0.06
    �
    0.06
    emer
    0.06
    Act Density 0.136%

    No Known Activations