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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numeros
    -0.07
    Fred
    -0.07
    .sav
    -0.06
    tie
    -0.06
     Fred
    -0.06
     felt
    -0.06
     Chevrolet
    -0.06
    .more
    -0.06
     BUG
    -0.06
    .”↵↵
    -0.06
    POSITIVE LOGITS
     것으로
    0.07
     shipped
    0.07
    們
    0.06
    序
    0.06
    quisites
    0.06
    aims
    0.06
     Evalu
    0.06
    �
    0.06
    体
    0.06
     Claims
    0.06
    Act Density 0.066%

    No Known Activations