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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Для
    -0.07
    enie
    -0.07
     drum
    -0.07
     amacı
    -0.07
    има
    -0.06
     Discounts
    -0.06
    loggedin
    -0.06
    	container
    -0.06
    ABILITY
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     detergent
    0.06
    。↵
    0.06
     commitment
    0.06
     mai
    0.06
    ?)↵
    0.06
    ']]],↵
    0.06
    <a
    0.06
     hops
    0.06
     beacon
    0.06
    .blocks
    0.06
    Act Density 0.018%

    No Known Activations