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

    Neuronpedia

    INDEX
    Explanations

    views

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doctor
    -0.07
    riors
    -0.06
    stoupil
    -0.06
     eat
    -0.06
    alnum
    -0.06
    Ru
    -0.06
    ежать
    -0.06
     thieves
    -0.06
    ECTOR
    -0.06
     erhalten
    -0.06
    POSITIVE LOGITS
     거
    0.07
    UF
    0.07
     bamb
    0.07
     nær
    0.06
    >
↵
↵
↵
    0.06
     loài
    0.06
     компон
    0.06
    306
    0.06
     imgs
    0.06
     distant
    0.06
    Act Density 0.011%

    No Known Activations