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

    Neuronpedia

    INDEX
    Explanations

    impeding progress or ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.90
    was
    0.84
     Community
    0.84
    che
    0.78
     Disorder
    0.77
    ys
    0.76
     School
    0.75
    by
    0.73
     Media
    0.73
     Про
    0.73
    POSITIVE LOGITS
     impede
    1.01
     répond
    0.98
     hindering
    0.98
     hinders
    0.97
     pince
    0.92
     jeopardize
    0.90
     jeopard
    0.88
     hindrance
    0.88
     impeded
    0.86
     impair
    0.83
    Act Density 0.128%

    No Known Activations