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

    Neuronpedia

    INDEX
    Explanations

    Technical issues/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rail
    -0.07
     Бол
    -0.07
     accounting
    -0.07
     yok
    -0.07
    یر
    -0.06
    ヘ
    -0.06
     suitable
    -0.06
     combinations
    -0.06
    viol
    -0.06
    兩
    -0.06
    POSITIVE LOGITS
     Gly
    0.07
     olmasına
    0.06
    _Pre
    0.06
    ################
    0.06
     svens
    0.06
    VERTISEMENT
    0.06
     اوت
    0.06
    /window
    0.06
    _DIS
    0.06
     σχ
    0.06
    Act Density 0.127%

    No Known Activations