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

    Neuronpedia

    INDEX
    Explanations

    making or allowing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이용하여
    0.51
     katika
    0.49
     adrift
    0.49
     کیسے
    0.48
     چگونه
    0.48
    elenggarakan
    0.48
     out
    0.48
     bewild
    0.47
     الى
    0.47
     together
    0.47
    POSITIVE LOGITS
    一定的
    0.44
    稍
    0.39
     এর
    0.38
     इसका
    0.37
     Ret
    0.37
     néhány
    0.37
    一些
    0.36
     कुछ
    0.36
     थोड़ी
    0.36
     `=`
    0.35
    Act Density 0.101%

    No Known Activations