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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wavelengths
    -0.07
     postal
    -0.06
     craz
    -0.06
     uniqueness
    -0.06
     Gat
    -0.06
     Spl
    -0.06
     English
    -0.06
     fewer
    -0.06
     Iowa
    -0.06
     jab
    -0.06
    POSITIVE LOGITS
    іли
    0.07
     componentDid
    0.07
    lerinin
    0.07
     proud
    0.07
    Ệ
    0.07
    lli
    0.06
    immer
    0.06
    alarını
    0.06
    (fragment
    0.06
     selectedItem
    0.06
    Act Density 0.004%

    No Known Activations