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

    Neuronpedia

    INDEX
    Explanations

    deep dive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tamanho
    0.37
     deemed
    0.37
    淡淡
    0.36
     esfuer
    0.35
    किसी
    0.35
     делать
    0.34
     دوسروں
    0.34
     लोड
    0.33
     ढेर
    0.32
     milder
    0.32
    POSITIVE LOGITS
    ening
    1.22
    ened
    1.09
    ness
    1.05
    est
    0.91
    nesses
    0.83
    ENING
    0.79
    ens
    0.77
    eners
    0.75
    ish
    0.73
    NESS
    0.71
    Act Density 0.153%

    No Known Activations