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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𬭊
    -0.08
     данных
    -0.07
     jj
    -0.07
     חדשים
    -0.07
    [index
    -0.07
     employees
    -0.07
    ydro
    -0.07
     фирм
    -0.07
     appoint
    -0.07
    𬣡
    -0.07
    POSITIVE LOGITS
    ouver
    0.07
    Overlay
    0.06
    _while
    0.06
     Santa
    0.06
     Saint
    0.06
    .querySelector
    0.06
    袁
    0.06
     quienes
    0.06
    仿
    0.06
    bear
    0.06
    Act Density 0.005%

    No Known Activations