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

    Neuronpedia

    INDEX
    Explanations

    outing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     première
    -0.07
     Northeast
    -0.07
    pleasant
    -0.06
    ■■
    -0.06
     propio
    -0.06
     haci
    -0.06
    _aw
    -0.06
    จำก
    -0.06
    ellido
    -0.06
    lovak
    -0.06
    POSITIVE LOGITS
     boots
    0.06
     booty
    0.06
    groupBox
    0.06
    aged
    0.06
    RATION
    0.06
     　　　　
    0.06
     captcha
    0.06
    Rock
    0.06
     woman
    0.06
    swire
    0.06
    Act Density 0.000%

    No Known Activations