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

    Neuronpedia

    INDEX
    Explanations

    BOOST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     п
    -0.07
    _nested
    -0.07
     parks
    -0.06
    ている
    -0.06
     SEARCH
    -0.06
    矿
    -0.06
    고
    -0.06
    Page
    -0.06
     white
    -0.06
     Nord
    -0.06
    POSITIVE LOGITS
    .xlabel
    0.08
    铘
    0.07
    VERBOSE
    0.07
     =======
    0.07
    嗞
    0.07
    髹
    0.07
     targets
    0.06
    ↤
    0.06
     автомат
    0.06
    年至
    0.06
    Act Density 0.005%

    No Known Activations