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

    Neuronpedia

    INDEX
    Explanations

    github links and datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getP
    0.69
    pare
    0.66
    ped
    0.66
    ಪೆ
    0.64
    पेपर
    0.62
    ppage
    0.62
    PAF
    0.60
    pras
    0.59
    Dem
    0.59
    alker
    0.58
    POSITIVE LOGITS
     Ammonia
    0.70
     am
    0.69
     ترم
    0.64
     ammonium
    0.62
     ammonia
    0.62
     shri
    0.62
    溪
    0.62
     Brook
    0.61
     Ram
    0.59
     kth
    0.58
    Act Density 0.210%

    No Known Activations