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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Row
    -0.07
     welding
    -0.06
     Paz
    -0.06
    .RESET
    -0.06
    /V
    -0.06
    Kal
    -0.06
     VOC
    -0.06
     Gel
    -0.06
     Meghan
    -0.06
     PAL
    -0.06
    POSITIVE LOGITS
     тех
    0.07
     forgiveness
    0.07
     shalt
    0.06
    　
    0.06
     erre
    0.06
     giao
    0.06
    ジ
    0.06
    -food
    0.06
    -message
    0.06
    足
    0.06
    Act Density 0.001%

    No Known Activations