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

    Neuronpedia

    INDEX
    Explanations

    process work steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )));
    0.80
     większość
    0.77
    ')),
    0.71
     MainForm
    0.69
    neigh
    0.68
     nettement
    0.67
    旛
    0.65
    ="";
    0.65
     cream
    0.65
    変わ
    0.64
    POSITIVE LOGITS
    dad
    0.81
    dst
    0.81
    ded
    0.80
    lo
    0.79
    deki
    0.78
     disamb
    0.77
    廂
    0.75
    ds
    0.74
    staat
    0.74
    果た
    0.74
    Act Density 0.290%

    No Known Activations