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

    Neuronpedia

    INDEX
    Explanations

    describes robot function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haft
    0.43
     پرا
    0.42
    原始内容存档
    0.41
     Tú
    0.41
    杞
    0.41
     আহমে
    0.40
    کرین
    0.40
     バイ
    0.38
     चुकी
    0.38
    जनबी
    0.38
    POSITIVE LOGITS
     powers
    0.44
     breat
    0.43
     meals
    0.39
     surplus
    0.39
     friendly
    0.38
     rap
    0.38
     gaze
    0.37
     removal
    0.36
     fever
    0.36
     sing
    0.36
    Act Density 0.000%

    No Known Activations