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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dog
    -0.07
    token
    -0.07
    [test
    -0.07
     bait
    -0.07
     Olsen
    -0.06
    theta
    -0.06
     token
    -0.06
    [t
    -0.06
     Kra
    -0.06
     don
    -0.06
    POSITIVE LOGITS
    �
    0.08
     Fach
    0.08
    /docs
    0.07
    роф
    0.07
    ::::
    0.07
    ी
    0.07
    inium
    0.07
    年に
    0.07
    �
    0.07
    �
    0.07
    Act Density 0.024%

    No Known Activations