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

    Neuronpedia

    INDEX
    Explanations

    focused on solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     provide
    0.52
     and
    0.48
     Provides
    0.47
     as
    0.46
     provides
    0.45
     indicate
    0.45
     providing
    0.44
     Est
    0.44
     archivo
    0.44
     Ann
    0.44
    POSITIVE LOGITS
    PROBLE
    0.44
    діть
    0.43
    𝓖
    0.43
    ปลี่ยน
    0.43
    ăpadă
    0.43
    φέρει
    0.42
    𝕡
    0.42
    uchs
    0.42
    ገር
    0.42
    ેર
    0.42
    Act Density 0.004%

    No Known Activations