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

    Neuronpedia

    INDEX
    Explanations

    file path and name matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    肌肤
    0.36
    砻
    0.36
    𝙖
    0.36
    但
    0.35
    肤
    0.34
    િમ
    0.34
    สัมพันธ์
    0.34
    现金
    0.33
    抒
    0.33
     유리
    0.32
    POSITIVE LOGITS
     -,
    0.38
     -"
    0.37
     -$
    0.36
     -\
    0.35
     Goll
    0.35
    周辺
    0.35
     Galleria
    0.35
     -.
    0.34
    ოთ
    0.34
    ństwa
    0.34
    Act Density 0.011%

    No Known Activations