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

    Neuronpedia

    INDEX
    Explanations

    descriptive list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    der
    0.51
    et
    0.44
    uh
    0.44
    0.43
    in
    0.42
    nings
    0.42
    ys
    0.41
    ptr
    0.41
    errated
    0.41
     சொ
    0.41
    POSITIVE LOGITS
     ejecutivo
    0.63
     această
    0.63
     scrittura
    0.61
    CHREIB
    0.60
     produzido
    0.59
     ondul
    0.59
     agrí
    0.58
     izgrad
    0.58
     industriale
    0.57
     comercio
    0.57
    Act Density 0.000%

    No Known Activations