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

    Neuronpedia

    INDEX
    Explanations

    launchpad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hear
    0.39
    風險
    0.38
    Risk
    0.38
     rischi
    0.37
    誕生
    0.37
    स्ति
    0.37
     ప్రజా
    0.36
    偉
    0.36
    ギュア
    0.35
     risk
    0.35
    POSITIVE LOGITS
    pad
    0.58
     pad
    0.55
    pads
    0.50
     Pad
    0.48
    Pad
    0.47
     keypad
    0.46
     CONTROL
    0.44
    パッド
    0.43
     pads
    0.42
     PAD
    0.41
    Act Density 0.001%

    No Known Activations