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

    Neuronpedia

    INDEX
    Explanations

    comprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /loader
    -0.09
    יע
    -0.08
     unconditional
    -0.08
    ложений
    -0.07
    Ͼ
    -0.07
    _
    -0.07
    牾
    -0.07
    otropic
    -0.07
     Oro
    -0.07
    辘
    -0.07
    POSITIVE LOGITS
     comprises
    0.08
    HasMaxLength
    0.07
     comprise
    0.07
    conde
    0.07
     complet
    0.07
     Emer
    0.07
    (def
    0.06
    [length
    0.06
    ｚ
    0.06
    (String
    0.06
    Act Density 0.009%

    No Known Activations