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

    Neuronpedia

    INDEX
    Explanations

    conservative lean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ружи
    0.49
     forgiving
    0.46
    по
    0.45
    lığını
    0.44
    вно
    0.43
    пас
    0.43
    ши
    0.43
     threatening
    0.43
    дами
    0.43
    诚信
    0.43
    POSITIVE LOGITS
     Makeup
    0.50
     Cake
    0.48
     Summer
    0.47
     Restaurant
    0.47
     Together
    0.46
     രണ്ടു
    0.46
     Tuscany
    0.45
     Trieste
    0.45
     Appet
    0.45
     केले
    0.45
    Act Density 0.000%

    No Known Activations