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

    Neuronpedia

    INDEX
    Explanations

    habit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oran
    -0.10
    ermen
    -0.10
    er
    -0.10
    oras
    -0.09
    ÑģÑĮ
    -0.09
    orida
    -0.09
    handler
    -0.09
    à¥ģà¤Ĺ
    -0.09
    itten
    -0.09
    yw
    -0.09
    POSITIVE LOGITS
    uated
    0.19
    uation
    0.19
    ually
    0.17
    acle
    0.14
     Habit
    0.14
    ué
    0.13
    uate
    0.13
    uary
    0.13
     Hab
    0.13
     habit
    0.12
    Act Density 0.019%

    No Known Activations