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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bedroom
    -0.07
     feet
    -0.07
    ่ง
    -0.07
    _damage
    -0.06
     decoration
    -0.06
    (pattern
    -0.06
     pus
    -0.06
    Soap
    -0.06
     Feet
    -0.06
     vibrating
    -0.06
    POSITIVE LOGITS
    ικα
    0.07
    vál
    0.07
    .*;
↵
    0.07
    asc
    0.06
    ："+
    0.06
     ;;=
    0.06
    """.
    0.06
     vulnerable
    0.06
     Romans
    0.06
     /*!<
    0.06
    Act Density 0.015%

    No Known Activations