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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，而且
    -0.09
    �
    -0.08
     יכול
    -0.07
    328
    -0.07
     niente
    -0.07
     состава
    -0.07
     llegado
    -0.07
     sapien
    -0.07
    ant
    -0.07
     podremos
    -0.07
    POSITIVE LOGITS
     denote
    0.14
     denotes
    0.10
    暂
    0.09
     করি
    0.08
     Hiro
    0.08
     എന്നു
    0.08
     shorthand
    0.08
     обознач
    0.08
     nech
    0.08
     hypot
    0.08
    Act Density 0.100%

    No Known Activations