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

    Neuronpedia

    INDEX
    Explanations

    health-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.82
     kasarigan
    -0.82
    DockStyle
    -0.79
    MessageOf
    -0.79
    RegressionTest
    -0.77
    principalColumn
    -0.73
    writeFieldEnd
    -0.73
    QMetaType
    -0.72
     CreateTagHelper
    -0.72
    Билгалдахарш
    -0.72
    POSITIVE LOGITS
     ervan
    0.39
     surgir
    0.39
    direct
    0.39
    ุน
    0.37
     farlo
    0.36
     vägen
    0.36
     terang
    0.36
     directo
    0.35
    POM
    0.35
     davon
    0.35
    Act Density 0.005%

    No Known Activations