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

    Neuronpedia

    INDEX
    Explanations

    actions to perform or handle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐬
    1.57
    𝐭
    1.56
    ل
    1.47
    ان
    1.38
     વખતે
    1.32
    𝐚
    1.23
    ために
    1.22
    לע
    1.22
    𝐮
    1.21
    રિક
    1.21
    POSITIVE LOGITS
     qw
    1.31
    se
    1.27
     concomit
    1.20
    μαν
    1.19
    horns
    1.16
     iteratively
    1.16
    clearRect
    1.14
    acetate
    1.12
    lega
    1.12
     angesch
    1.11
    Act Density 0.000%

    No Known Activations