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

    Neuronpedia

    INDEX
    Explanations

    goals and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assi
    0.47
     ਨ
    0.45
     odnosu
    0.45
     ajal
    0.45
     અન્ય
    0.44
     udara
    0.44
     ടെ
    0.44
     اہم
    0.44
     apni
    0.44
     enfermed
    0.43
    POSITIVE LOGITS
    念
    0.44
    ف
    0.41
    ‍
    0.38
    Similar
    0.38
    化
    0.38
    ны
    0.38
    察
    0.37
    구요
    0.36
    遥
    0.36
    comings
    0.36
    Act Density 0.000%

    No Known Activations