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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deutschland
    -0.07
    하였다
    -0.07
     rekl
    -0.07
     internals
    -0.07
    strength
    -0.06
     случай
    -0.06
     CORE
    -0.06
     Tara
    -0.06
     Nội
    -0.06
    绝
    -0.06
    POSITIVE LOGITS
     Treasure
    0.08
    _Title
    0.07
    rollment
    0.07
    Vector
    0.07
    .Authentication
    0.07
    _LOWER
    0.06
    Poss
    0.06
     Katz
    0.06
    lope
    0.06
    кет
    0.06
    Act Density 0.000%

    No Known Activations