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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treats
    -0.07
     xúc
    -0.07
    rary
    -0.07
    评论
    -0.07
     taxes
    -0.06
     mãe
    -0.06
    ourced
    -0.06
     diyor
    -0.06
    考虑
    -0.06
     algunas
    -0.06
    POSITIVE LOGITS
    KEY
    0.06
    تف
    0.06
     الثالث
    0.06
    lazy
    0.06
    string
    0.06
    FIG
    0.06
    とする
    0.06
     Probe
    0.06
    PUBLIC
    0.06
     Concurrent
    0.06
    Act Density 0.024%

    No Known Activations