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

    Neuronpedia

    INDEX
    Explanations

    fs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fourteen
    -0.07
     of
    -0.07
     Julian
    -0.07
     von
    -0.06
     telefon
    -0.06
    .BigInteger
    -0.06
    /k
    -0.06
    Tony
    -0.06
     Milton
    -0.06
    cone
    -0.06
    POSITIVE LOGITS
    itial
    0.08
    atively
    0.08
     الإسرائيل
    0.07
    工具
    0.07
     heavier
    0.07
    泇
    0.07
    싲
    0.07
     SSH
    0.07
     internals
    0.07
     ipt
    0.07
    Act Density 0.014%

    No Known Activations