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

    Neuronpedia

    INDEX
    Explanations

    connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notes
    0.97
    ご注意
    0.97
     vous
    0.94
     note
    0.91
     Anda
    0.88
     wry
    0.83
     salvo
    0.80
     usual
    0.80
     attr
    0.77
     willkommen
    0.77
    POSITIVE LOGITS
     Cependant
    1.39
    Furthermore
    1.37
     Furthermore
    1.35
     Firstly
    1.33
    또한
    1.29
    Firstly
    1.25
     Therefore
    1.25
     또한
    1.24
     jedoch
    1.23
    但是
    1.22
    Act Density 0.029%

    No Known Activations