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

    Neuronpedia

    INDEX
    Explanations

    accuracy, easiest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theses
    0.86
    妳
    0.86
     memoirs
    0.79
     morphisms
    0.79
     happenings
    0.78
     arouse
    0.77
     clipart
    0.76
     writings
    0.76
     awaken
    0.75
     arduino
    0.75
    POSITIVE LOGITS
    retail
    0.74
    衡量
    0.74
    agement
    0.73
    urando
    0.69
    nance
    0.68
    UK
    0.66
    novation
    0.66
    believe
    0.66
    但
    0.66
    然而
    0.65
    Act Density 0.004%

    No Known Activations