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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .find
    -0.08
     جد
    -0.07
     economical
    -0.07
    olis
    -0.06
     vegetation
    -0.06
     누
    -0.06
     liebe
    -0.06
     fue
    -0.06
    bett
    -0.06
     cle
    -0.06
    POSITIVE LOGITS
    ög
    0.06
    SITE
    0.06
    —"
    0.06
    &)↵
    0.06
     rapp
    0.06
    Trad
    0.06
    ($.
    0.06
     přih
    0.06
    _COMPANY
    0.06
    /Object
    0.06
    Act Density 0.047%

    No Known Activations