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

    Neuronpedia

    INDEX
    Explanations

    together

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kf
    -0.07
     translates
    -0.07
     shines
    -0.06
    _client
    -0.06
     metodo
    -0.06
     served
    -0.06
    请求
    -0.06
     searchText
    -0.06
     시스템
    -0.06
    Pacific
    -0.06
    POSITIVE LOGITS
     assembling
    0.08
     затвердж
    0.07
     dicks
    0.07
     Associate
    0.07
     assemble
    0.07
    蛛
    0.07
    sembling
    0.07
    ">',
    0.07
     Swap
    0.06
    STANCE
    0.06
    Act Density 0.010%

    No Known Activations