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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xt
    -0.07
     حل
    -0.07
     endorsing
    -0.07
     Searching
    -0.07
     chorus
    -0.07
     centerX
    -0.06
     DataColumn
    -0.06
     merry
    -0.06
    -election
    -0.06
    _finder
    -0.06
    POSITIVE LOGITS
     Ukraj
    0.07
    _paint
    0.06
    (plot
    0.06
    िण
    0.06
    _surface
    0.06
    omega
    0.06
     approvals
    0.06
    َك
    0.06
    isyon
    0.06
     ){
↵
    0.06
    Act Density 0.210%

    No Known Activations