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

    Neuronpedia

    INDEX
    Explanations

    Óscar, éth, úth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    很多的
    1.41
    д
    1.28
     economies
    1.26
    ename
    1.26
    дың
    1.25
     Stacy
    1.24
    ıy
    1.23
     atheros
    1.22
    ్
    1.22
    ı
    1.22
    POSITIVE LOGITS
    na
    1.71
    ns
    1.64
    s
    1.62
    sulf
    1.57
    rmse
    1.55
    ptăm
    1.54
    ng
    1.52
    ské
    1.51
    nder
    1.47
    nergie
    1.44
    Act Density 0.337%

    No Known Activations