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

    Neuronpedia

    INDEX
    Explanations

    excellent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neighbour
    -0.07
     Mandal
    -0.07
     map
    -0.07
    ीग
    -0.06
     mediation
    -0.06
    _fil
    -0.06
    ifestyle
    -0.06
    Doing
    -0.06
    aying
    -0.06
    ')↵↵↵
    -0.06
    POSITIVE LOGITS
     excellent
    0.12
     Excellent
    0.09
     outstanding
    0.09
    Excellent
    0.08
     stellar
    0.08
    صب
    0.08
     excelente
    0.08
     impeccable
    0.08
     отлич
    0.07
     excell
    0.07
    Act Density 0.013%

    No Known Activations