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

    Neuronpedia

    INDEX
    Explanations

    angle brackets or parentheses, likely as part of HTML or URLs

    oai_token-act-pair · gemini-2.0-flash

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الحره
    -0.48
     sums
    -0.47
    illium
    -0.47
    Lähteet
    -0.46
     Courant
    -0.45
    umina
    -0.45
     lobes
    -0.44
     courseId
    -0.44
     Amb
    -0.43
    MENAFN
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.68
     armées
    0.66
     souverain
    0.66
     étoit
    0.65
    sizeCache
    0.63
     avoient
    0.62
    }))
    0.60
     المعيارى
    0.59
     démocr
    0.59
     chré
    0.59
    Act Density 1.439%

    No Known Activations