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

    Neuronpedia

    INDEX
    Explanations

    Driver Display malfunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nya
    1.36
     ceasefire
    1.36
     vải
    1.29
     cubrir
    1.28
     избежать
    1.27
    চট্টগ্রাম
    1.25
     belakang
    1.24
     deeds
    1.15
    etermined
    1.15
     receivable
    1.14
    POSITIVE LOGITS
    е
    1.06
    ergy
    1.03
    vul
    0.97
    v
    0.96
    າ
    0.94
    во
    0.93
    ोग
    0.92
    ності
    0.92
    ಷ್ಠ
    0.92
    0.92
    Act Density 0.002%

    No Known Activations