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

    Neuronpedia

    INDEX
    Explanations

    operations on entities ending in parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :'',
    0.45
    =
    0.45
    :
    0.41
    :,
    0.41
    upe
    0.40
    =`
    0.40
    elde
    0.37
     versatile
    0.37
     जाया
    0.37
    டாக
    0.37
    POSITIVE LOGITS
     〢
    0.47
     除了
    0.45
     phẳng
    0.44
     输出
    0.43
     输入
    0.41
     设置
    0.40
    λια
    0.40
     criança
    0.40
    输入
    0.39
    冲击
    0.39
    Act Density 0.005%

    No Known Activations