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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     happiest
    -0.07
     小
    -0.07
     LEGO
    -0.07
     Sas
    -0.07
     Prostitutas
    -0.06
     unregister
    -0.06
     �
    -0.06
    ﺘ
    -0.06
     должна
    -0.06
     Nissan
    -0.06
    POSITIVE LOGITS
    ADE
    0.07
    anst
    0.07
     bel
    0.06
     ،
    0.06
     reconstruct
    0.06
     wrapped
    0.06
     wolves
    0.06
    =int
    0.06
    ade
    0.06
     companions
    0.06
    Act Density 0.000%

    No Known Activations