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

    Neuronpedia

    INDEX
    Explanations

    cannot fulfill requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     narciss
    0.87
     ure
    0.82
     perv
    0.81
     repl
    0.74
     newborn
    0.73
     রাখুন
    0.73
     terror
    0.73
     deth
    0.73
     propylene
    0.72
     sound
    0.72
    POSITIVE LOGITS
    نا
    0.79
    غ
    0.72
    ح
    0.72
    در
    0.70
    መ
    0.69
    خ
    0.68
    נה
    0.68
    حد
    0.67
    عد
    0.65
    ست
    0.64
    Act Density 0.034%

    No Known Activations