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

    Neuronpedia

    INDEX
    Explanations

    not followed by qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     não
    0.49
     না
    0.48
    não
    0.46
     אין
    0.46
     ikke
    0.46
     nicht
    0.45
    Nicht
    0.45
     לא
    0.45
     Não
    0.44
    Não
    0.44
    POSITIVE LOGITS
     necessarily
    0.74
     obstante
    0.55
    orious
    0.53
     dissimilar
    0.50
     unlike
    0.49
     deterred
    0.48
     hề
    0.48
    hin
    0.47
    necessarily
    0.46
    ching
    0.46
    Act Density 0.321%

    No Known Activations