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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     louder
    -0.07
     salle
    -0.07
     jobId
    -0.06
     learns
    -0.06
     atroc
    -0.06
     lifes
    -0.06
     conceivable
    -0.06
     dolar
    -0.06
     sandwiches
    -0.06
     пан
    -0.06
    POSITIVE LOGITS
    sel
    0.07
    diğini
    0.07
     från
    0.07
    ,
    0.07
    -dropdown
    0.07
     دفتر
    0.06
    acağım
    0.06
     설
    0.06
    (dataSource
    0.06
    gesture
    0.06
    Act Density 0.000%

    No Known Activations