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

    Neuronpedia

    INDEX
    Explanations

    Communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traités
    -0.56
     cérami
    -0.54
     thèmes
    -0.53
     lèvres
    -0.52
     vägen
    -0.52
     blessés
    -0.51
     cœurs
    -0.51
     malades
    -0.50
     peines
    -0.48
    ellery
    -0.48
    POSITIVE LOGITS
    TypedDataSet
    0.75
     समीक्षाएं
    0.70
    ⓧ
    0.68
    SpringBootTest
    0.68
     nahilalakip
    0.67
    WriteBarrier
    0.66
    IUrlHelper
    0.65
    djangoproject
    0.65
     apostles
    0.63
    #+#
    0.63
    Act Density 0.313%

    No Known Activations