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

    Neuronpedia

    INDEX
    Explanations

    foreign words and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.47
    does
    0.45
     epi
    0.44
     francs
    0.42
    ，
    0.42
    еты
    0.41
     does
    0.41
     initiates
    0.41
     blanca
    0.40
     jun
    0.39
    POSITIVE LOGITS
    вання
    0.57
    ৩৫
    0.52
    3
    0.50
    lust
    0.50
    vers
    0.49
     Versicher
    0.49
     వచ్చ
    0.48
    ओं
    0.48
    TAIN
    0.47
    unya
    0.47
    Act Density 0.000%

    No Known Activations