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

    Neuronpedia

    INDEX
    Explanations

    task, job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    melon
    -0.07
    zeros
    -0.07
    电影
    -0.06
    onga
    -0.06
    sku
    -0.06
    rz
    -0.06
    ERO
    -0.06
    ocado
    -0.06
    requency
    -0.06
    disconnect
    -0.06
    POSITIVE LOGITS
     envis
    0.07
     CBS
    0.07
     enumerable
    0.06
     declar
    0.06
     TAS
    0.06
     thỏa
    0.06
     preced
    0.06
     Kami
    0.06
    .currentIndex
    0.06
    .scene
    0.06
    Act Density 0.024%

    No Known Activations