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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kwargs
    -0.07
    wargs
    -0.07
     Pru
    -0.06
    upe
    -0.06
    óng
    -0.06
    ctp
    -0.06
     chewing
    -0.06
    сем
    -0.06
     zdrav
    -0.06
     nhựa
    -0.06
    POSITIVE LOGITS
     текущ
    0.07
    LOOK
    0.06
    erne
    0.06
    ystery
    0.06
     inning
    0.06
    923
    0.06
    =find
    0.06
    _goals
    0.06
    connect
    0.06
    _iterations
    0.06
    Act Density 0.000%

    No Known Activations