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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Idx
    -0.07
     jejichž
    -0.06
    charts
    -0.06
    [w
    -0.06
     bat
    -0.06
    nk
    -0.06
     accessed
    -0.06
    ektir
    -0.06
    ["+
    -0.06
     waypoint
    -0.06
    POSITIVE LOGITS
     모
    0.07
    بي
    0.07
    \Product
    0.06
     shipped
    0.06
     الاخ
    0.06
    라도
    0.06
    atcher
    0.06
     antim
    0.06
     diverted
    0.06
    .Modified
    0.06
    Act Density 0.032%

    No Known Activations