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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transparent
    -0.07
     væ
    -0.07
     elsif
    -0.07
    عف
    -0.07
     ries
    -0.06
     litre
    -0.06
     invis
    -0.06
     Seats
    -0.06
     olmam
    -0.06
     Olsen
    -0.06
    POSITIVE LOGITS
    <table
    0.07
    마다
    0.07
    前的
    0.06
    inerary
    0.06
    ублі
    0.06
    Hook
    0.06
    (IDC
    0.06
    .RequestBody
    0.06
    Assign
    0.06
    imestep
    0.06
    Act Density 0.107%

    No Known Activations