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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нім
    -0.08
    COD
    -0.06
     खर
    -0.06
    IW
    -0.06
    aw
    -0.06
    隆
    -0.06
     Flow
    -0.06
    Salir
    -0.06
    .un
    -0.06
    AW
    -0.06
    POSITIVE LOGITS
    EA
    0.07
     these
    0.06
    となり
    0.06
    uč
    0.06
    _PROFILE
    0.06
     사람은
    0.06
     П
    0.06
    atu
    0.06
     warns
    0.06
     kry
    0.06
    Act Density 0.007%

    No Known Activations