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

    Neuronpedia

    INDEX
    Explanations

    github repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     —
    -2.48
    ﾈ
    -2.45
     Moreover
    -2.42
    “
    -2.42
     jovial
    -2.39
     Furthermore
    -2.39
    苙
    -2.34
     Certainly
    -2.30
     Consequently
    -2.28
     Also
    -2.25
    POSITIVE LOGITS
    幛
    2.64
    穑
    2.56
     activado
    2.38
    2.38
     abiye
    2.34
    茕
    2.33
    ༵
    2.33
    鹬
    2.31
     vivió
    2.31
    学校の
    2.30
    Act Density 0.012%

    No Known Activations