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

    Neuronpedia

    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .require
    -0.08
    /C
    -0.08
     Rapids
    -0.07
    _REQUIRE
    -0.07
     adlı
    -0.07
    oron
    -0.07
     എണ്ണം
    -0.07
    .substr
    -0.07
     Require
    -0.07
     nilo
    -0.07
    POSITIVE LOGITS
     amenities
    0.11
    Amenities
    0.11
     Amenities
    0.11
     spacious
    0.10
     woonkamer
    0.09
     hospitality
    0.09
     amén
    0.09
     dining
    0.09
     भोजन
    0.08
    Advantages
    0.08
    Act Density 0.020%

    No Known Activations