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

    Neuronpedia

    INDEX
    Explanations

    stop, continue, receive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >>>
    0.39
    CB
    0.38
    ্লা
    0.36
    Paris
    0.36
    Cities
    0.36
    オープン
    0.36
    Hers
    0.35
     відкри
    0.35
     coval
    0.34
    Trung
    0.34
    POSITIVE LOGITS
     submit
    0.52
    submit
    0.50
     요청
    0.50
     request
    0.47
    𝕄
    0.47
     quaerat
    0.46
     wishes
    0.46
     souha
    0.44
     submitting
    0.43
     submissions
    0.43
    Act Density 0.000%

    No Known Activations