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

    Neuronpedia

    INDEX
    Explanations

    reaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conflicts
    -0.07
     carga
    -0.07
    -----------
    -0.07
     vypl
    -0.07
     Legendary
    -0.06
     işaret
    -0.06
     colorful
    -0.06
    anuts
    -0.06
     buffer
    -0.06
     خدمات
    -0.06
    POSITIVE LOGITS
    님이
    0.07
     ev
    0.06
    ;
↵
↵
↵
↵
    0.06
    .players
    0.06
     reaction
    0.06
     Regents
    0.06
    ]:
    0.06
     ];↵↵
    0.06
    ();}↵
    0.06
    ็ค
    0.06
    Act Density 0.017%

    No Known Activations