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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DIALOG
    -0.07
    Location
    -0.07
     discovery
    -0.07
     Feb
    -0.06
    ива
    -0.06
     رفت
    -0.06
    viz
    -0.06
    获
    -0.06
     tier
    -0.06
    Figure
    -0.06
    POSITIVE LOGITS
    .sorted
    0.07
    uniacid
    0.07
     disproportion
    0.06
    */,↵
    0.06
     تلك
    0.06
    irut
    0.06
     strategist
    0.06
     distorted
    0.06
     stát
    0.06
     واحد
    0.06
    Act Density 0.288%

    No Known Activations