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
    065
    -0.07
    alez
    -0.07
     státní
    -0.06
     GAS
    -0.06
     Raz
    -0.06
    UCE
    -0.06
    uce
    -0.06
    463
    -0.06
    tim
    -0.06
    ‌کننده
    -0.06
    POSITIVE LOGITS
     substitutes
    0.07
    auen
    0.06
    Early
    0.06
    bis
    0.06
     difficulty
    0.06
     stayed
    0.06
     regenerate
    0.06
     }?>↵
    0.06
    maf
    0.06
    .navigationBar
    0.06
    Act Density 0.016%

    No Known Activations