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

    Neuronpedia

    INDEX
    Explanations

    this is or this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moze
    0.52
     sempat
    0.49
     might
    0.49
     potentially
    0.47
     grenade
    0.47
     alphanumeric
    0.46
     may
    0.45
     muffled
    0.45
     potrebbe
    0.45
     möglicherweise
    0.44
    POSITIVE LOGITS
    就是要
    0.61
    это
    0.58
    This
    0.56
    我们要
    0.54
    这就是
    0.54
    Creating
    0.52
    Ultimately
    0.52
    Это
    0.51
     это
    0.50
    Each
    0.50
    Act Density 0.095%

    No Known Activations