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

    Neuronpedia

    INDEX
    Explanations

    Del

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relentless
    -0.08
     القرار
    -0.07
     evaluating
    -0.07
    �
    -0.07
     Transaction
    -0.07
    ฟ
    -0.07
     إطار
    -0.07
    !’
    -0.06
    ながら
    -0.06
    Ocean
    -0.06
    POSITIVE LOGITS
     литератур
    0.07
    🖱
    0.06
    Camp
    0.06
     certificate
    0.06
    schlä
    0.06
    setup
    0.06
     license
    0.06
    スタッ
    0.06
    prim
    0.06
     annotations
    0.06
    Act Density 0.495%

    No Known Activations