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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    核
    -0.07
     acknowledgment
    -0.07
    tooltip
    -0.06
    طه
    -0.06
    uels
    -0.06
     JAXB
    -0.06
    fully
    -0.06
    children
    -0.06
    pagination
    -0.06
     mirrors
    -0.06
    POSITIVE LOGITS
    volatile
    0.07
    >Main
    0.07
    Summer
    0.06
    egal
    0.06
     iteration
    0.06
     Prec
    0.06
     pls
    0.06
     electrical
    0.06
     stockholm
    0.06
     '))↵
    0.06
    Act Density 0.517%

    No Known Activations