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

    Neuronpedia

    INDEX
    Explanations

    which, losing, with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rope
    0.45
     prona
    0.42
     indulgence
    0.42
     fo
    0.42
     extravagance
    0.41
     samos
    0.41
     handcrafted
    0.40
     peppermint
    0.40
     germinate
    0.40
     erred
    0.40
    POSITIVE LOGITS
    |
    0.43
     {
    0.41
     Mikey
    0.40
    ؛
    0.38
    urches
    0.37
    Tony
    0.36
     McGr
    0.36
     المقد
    0.36
    Neil
    0.36
    urie
    0.36
    Act Density 0.000%

    No Known Activations