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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indices
    -0.06
     flies
    -0.06
    ẹ
    -0.06
     wreckage
    -0.06
     remarks
    -0.06
    ]'↵
    -0.06
    об
    -0.06
     webView
    -0.06
     dív
    -0.06
    canvas
    -0.06
    POSITIVE LOGITS
     isAuthenticated
    0.07
    _PLACE
    0.07
    テル
    0.07
    _aug
    0.06
     مقدار
    0.06
    _SPR
    0.06
     Double
    0.06
     Gig
    0.06
    <article
    0.06
     三
    0.06
    Act Density 0.010%

    No Known Activations