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

    Neuronpedia

    INDEX
    Explanations

    Code/Puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     versatility
    -0.07
     rather
    -0.07
     RNA
    -0.06
    Thin
    -0.06
    tures
    -0.06
     altogether
    -0.06
     других
    -0.06
     slashing
    -0.06
    ・
    -0.06
     Coord
    -0.06
    POSITIVE LOGITS
     حض
    0.07
    AILS
    0.07
     đậu
    0.06
    (elements
    0.06
    能
    0.06
    _fit
    0.06
     Grocery
    0.06
     useForm
    0.06
    away
    0.06
    .keySet
    0.06
    Act Density 0.001%

    No Known Activations