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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     защ
    -0.07
     litter
    -0.06
    Always
    -0.06
     Simply
    -0.06
    ुज
    -0.06
     tvoří
    -0.06
    Cy
    -0.06
    环
    -0.06
    'im
    -0.06
     Sal
    -0.06
    POSITIVE LOGITS
    _TEMP
    0.08
     &↵
    0.07
    '}↵↵
    0.07
     ;
↵
    0.06
     ela
    0.06
    %)↵↵
    0.06
     %↵↵
    0.06
    _exact
    0.06
     extern
    0.06
     eventName
    0.06
    Act Density 0.016%

    No Known Activations