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

    Neuronpedia

    INDEX
    Explanations

    positive superlatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     otras
    -0.06
    -city
    -0.06
    pressure
    -0.06
    _robot
    -0.06
    isure
    -0.06
     Petro
    -0.06
     ситуации
    -0.06
     hous
    -0.06
     شهرد
    -0.06
    POSITIVE LOGITS
     qualified
    0.07
    nor
    0.06
     wishlist
    0.06
    stable
    0.06
    (target
    0.06
    览
    0.06
     Benchmark
    0.06
     VS
    0.06
    Extern
    0.06
     Lucas
    0.06
    Act Density 0.019%

    No Known Activations