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

    Neuronpedia

    INDEX
    Explanations

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ne
    0.54
    ל
    0.52
    ن
    0.50
    е
    0.50
    ר
    0.49
    内
    0.49
    ב
    0.49
    ل
    0.49
    lo
    0.48
    w
    0.48
    POSITIVE LOGITS
    mainframe
    0.50
     এদেশে
    0.45
     topography
    0.45
    Scoped
    0.43
    estamp
    0.41
    Hf
    0.41
     terjadinya
    0.41
     paci
    0.41
     sunsets
    0.41
     melanjutkan
    0.41
    Act Density 0.000%

    No Known Activations