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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    六
    -0.06
    ット
    -0.06
     malls
    -0.06
    พร
    -0.06
    ocial
    -0.06
    lastic
    -0.06
     Florence
    -0.06
    ěst
    -0.06
    싱
    -0.06
    BLUE
    -0.06
    POSITIVE LOGITS
    INavigation
    0.07
    InThe
    0.07
    _amp
    0.07
    .initialize
    0.06
     ↵↵
    0.06
    て
    0.06
    _pd
    0.06
     dg
    0.06
     Individuals
    0.06
    луги
    0.06
    Act Density 0.005%

    No Known Activations