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

    Neuronpedia

    INDEX
    Explanations

    confident

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uninitialized
    -0.07
     vysoké
    -0.07
     Ear
    -0.06
    �
    -0.06
    Santa
    -0.06
     Evening
    -0.06
     geopolitical
    -0.06
    変わ
    -0.06
     Tories
    -0.06
     Aur
    -0.06
    POSITIVE LOGITS
    erner
    0.07
    視
    0.06
    (pk
    0.06
    см
    0.06
    _WRAPPER
    0.06
    _PB
    0.06
    RA
    0.06
     натураль
    0.06
     researched
    0.06
     Wald
    0.06
    Act Density 0.029%

    No Known Activations