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

    Neuronpedia

    INDEX
    Explanations

    Explaining a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     additionally
    0.42
     ayrıca
    0.41
     inoltre
    0.41
     همچنین
    0.40
     zudem
    0.39
     Ayrıca
    0.38
     außerdem
    0.38
     также
    0.37
     також
    0.37
     Asimismo
    0.37
    POSITIVE LOGITS
    Firstly
    0.60
    Fund
    0.52
    首先
    0.51
    Imagine
    0.51
    Forget
    0.50
    まず
    0.50
    Think
    0.49
    Okay
    0.48
    Traditionally
    0.48
    Unlike
    0.47
    Act Density 0.539%

    No Known Activations