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

    Neuronpedia

    INDEX
    Explanations

    specific words and subsequent phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ウター
    0.45
    ostomy
    0.44
    пей
    0.42
    瓯
    0.42
    ние
    0.42
    തന്നെ
    0.42
    قي
    0.41
    igos
    0.41
    вые
    0.41
    zneim
    0.41
    POSITIVE LOGITS
     rendah
    0.51
    razia
    0.50
     berpikir
    0.47
     Curator
    0.46
    circa
    0.45
     rates
    0.44
     commanded
    0.44
     kép
    0.44
    ngen
    0.44
     certiorari
    0.44
    Act Density 0.000%

    No Known Activations