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

    Neuronpedia

    INDEX
    Explanations

    Roughly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itch
    0.40
    better
    0.38
    UL
    0.38
     repealed
    0.38
     বিচ
    0.38
     reformulated
    0.38
    thai
    0.38
     oportunidad
    0.37
    KS
    0.37
     কর
    0.37
    POSITIVE LOGITS
     rough
    0.98
    Rough
    0.94
     Rough
    0.88
    rough
    0.78
    粗
    0.77
     roug
    0.71
     roughness
    0.68
     estimate
    0.68
    糙
    0.63
    Estimate
    0.61
    Act Density 0.010%

    No Known Activations