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

    Neuronpedia

    INDEX
    Explanations

    number 2 or 3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flows
    -0.06
    .weixin
    -0.06
    $i
    -0.06
    І
    -0.06
     yerinde
    -0.06
    Inserted
    -0.06
     correlations
    -0.06
    .change
    -0.06
    orris
    -0.06
    getValue
    -0.06
    POSITIVE LOGITS
     apare
    0.07
    ],"
    0.07
     Screens
    0.07
     thrilled
    0.07
     Eph
    0.06
     Oman
    0.06
    ]."
    0.06
     Сан
    0.06
    win
    0.06
     MAR
    0.06
    Act Density 0.049%

    No Known Activations