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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :invoke
    -0.07
     לצפיה
    -0.07
    ナン
    -0.07
    Maint
    -0.07
     south
    -0.07
    hwnd
    -0.07
    xmin
    -0.07
    Strange
    -0.07
    Word
    -0.07
     HOME
    -0.06
    POSITIVE LOGITS
    からは
    0.08
    erea
    0.08
    죳
    0.07
    })
    0.07
    (Y
    0.06
    _REFERER
    0.06
    (SC
    0.06
     חוק
    0.06
    聿
    0.06
     Mayer
    0.06
    Act Density 0.002%

    No Known Activations