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

    Neuronpedia

    INDEX
    Explanations

    onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     f
    0.72
     be
    0.70
    ias
    0.70
    ining
    0.68
    abe
    0.65
    adas
    0.64
     propon
    0.62
    ail
    0.62
    za
    0.61
    y
    0.61
    POSITIVE LOGITS
    在
    0.74
     in
    0.67
     waarde
    0.66
    ᾗ
    0.65
    ന്ന്
    0.64
    Editorial
    0.64
     Directeur
    0.63
    ંત્રણ
    0.61
    Promotion
    0.61
    Literatura
    0.61
    Act Density 0.006%

    No Known Activations