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

    Neuronpedia

    INDEX
    Explanations

    covering or encircling things/people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    1.06
     gegenüber
    0.98
    facing
    0.97
    at
    0.90
    it
    0.89
    ют
    0.87
     consecutive
    0.86
    on
    0.84
    0.82
    ेंगे
    0.81
    POSITIVE LOGITS
     bandages
    1.29
     coils
    1.23
     hissed
    1.19
    yzed
    1.16
     decoded
    1.14
     cocoon
    1.13
     espalda
    1.12
     ocor
    1.12
     encased
    1.11
    疹
    1.11
    Act Density 0.062%

    No Known Activations