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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    धी
    -0.08
    ادية
    -0.08
     inauguration
    -0.08
     president
    -0.07
     действие
    -0.07
     sidan
    -0.07
     Dodgers
    -0.07
    ederen
    -0.07
    žeme
    -0.07
     golfer
    -0.07
    POSITIVE LOGITS
     хранения
    0.11
     storing
    0.10
     buffers
    0.10
     stockage
    0.09
     storage
    0.09
     sizable
    0.09
     sizeable
    0.09
     accum
    0.09
    buffers
    0.08
     retained
    0.08
    Act Density 0.007%

    No Known Activations