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

    Neuronpedia

    INDEX
    Explanations

    Code, citations, abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ื
    -0.07
     �
    -0.07
     listOf
    -0.07
     горм
    -0.06
     извест
    -0.06
     Shepard
    -0.06
     Era
    -0.06
     Sacr
    -0.06
     drawing
    -0.06
    िद
    -0.06
    POSITIVE LOGITS
    opard
    0.07
     oui
    0.07
     réal
    0.06
    .AllowUser
    0.06
     durante
    0.06
    niej
    0.06
     squarely
    0.06
    conn
    0.06
    stvo
    0.06
    owner
    0.06
    Act Density 0.251%

    No Known Activations