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

    Neuronpedia

    INDEX
    Explanations

    technical condition or limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錘
    0.42
    >%
    0.42
     왕
    0.41
     洗
    0.41
     رضا
    0.41
     යු
    0.40
     वर्मा
    0.39
    壳
    0.39
    ኘ
    0.39
    Chal
    0.39
    POSITIVE LOGITS
     Scop
    0.40
    inging
    0.38
    ating
    0.38
    בוד
    0.38
     Recap
    0.36
    iset
    0.36
     gob
    0.35
     archiving
    0.35
     Sin
    0.35
    jing
    0.34
    Act Density 0.000%

    No Known Activations