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

    Neuronpedia

    INDEX
    Explanations

    criticizes opinion pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vasculature
    0.39
    leyebilirsiniz
    0.38
    Vý
    0.37
     perfusion
    0.37
    ≲
    0.37
    Aunque
    0.36
     dechlor
    0.36
    ángulos
    0.36
     ощу
    0.35
     isometry
    0.35
    POSITIVE LOGITS
     columnist
    0.65
     COLUMN
    0.58
    COLUMN
    0.54
     columna
    0.53
     Column
    0.52
     column
    0.52
    Column
    0.50
     politicians
    0.49
    column
    0.48
     coluna
    0.45
    Act Density 0.000%

    No Known Activations