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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yuk
    -0.08
     ro
    -0.08
     dramatically
    -0.08
     fra
    -0.08
     mirrors
    -0.07
     granted
    -0.07
     mant
    -0.07
     mirror
    -0.07
     स्म
    -0.07
    rought
    -0.07
    POSITIVE LOGITS
    Convention
    0.09
     শুন
    0.08
     Convention
    0.08
     সন্ধ
    0.08
    ীগ
    0.08
    =='
    0.08
     فإذا
    0.08
     contenus
    0.08
    =="
    0.08
    (INFO
    0.08
    Act Density 0.015%

    No Known Activations