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

    Neuronpedia

    INDEX
    Explanations

    tackle or solve problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مق
    0.48
    eng
    0.47
     Engineer
    0.46
    dent
    0.45
    day
    0.45
     Where
    0.44
    enging
    0.43
    documented
    0.43
    queryset
    0.43
    写入
    0.43
    POSITIVE LOGITS
     erythrocytes
    0.47
     conscientes
    0.46
     znacznie
    0.46
    ToArabic
    0.45
    <0x19>
    0.45
     diathermy
    0.44
     rápidamente
    0.44
     overestimated
    0.43
     Alemania
    0.43
     delimiters
    0.43
    Act Density 0.007%

    No Known Activations