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

    Neuronpedia

    INDEX
    Explanations

    Empty strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pee
    -0.07
    jis
    -0.06
    ercise
    -0.06
     現
    -0.06
     Uph
    -0.06
     EVE
    -0.06
    -pencil
    -0.06
     欧
    -0.06
    ятно
    -0.06
     Laurie
    -0.06
    POSITIVE LOGITS
    /tiny
    0.07
    рун
    0.07
    คาส
    0.07
    unting
    0.06
    (Client
    0.06
    (assert
    0.06
    Jack
    0.06
     στην
    0.06
    	xml
    0.06
     remotely
    0.06
    Act Density 0.000%

    No Known Activations