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

    Neuronpedia

    INDEX
    Explanations

    states that have been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chose
    0.46
     chooses
    0.45
     choose
    0.43
     knew
    0.38
     decides
    0.38
     forgot
    0.38
     забы
    0.37
    expérience
    0.37
     wrote
    0.36
    记得
    0.36
    POSITIVE LOGITS
     been
    0.92
     resulted
    0.77
    been
    0.74
     consisted
    0.66
     sido
    0.62
     varit
    0.62
     Been
    0.61
     BEEN
    0.61
     vært
    0.60
     evolved
    0.60
    Act Density 0.015%

    No Known Activations