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

    Neuronpedia

    INDEX
    Explanations

    code routing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INCLUDED
    -0.07
     преступ
    -0.07
    .Mar
    -0.06
    ,↵↵
    -0.06
    893
    -0.06
     {↵↵↵
    -0.06
     lubric
    -0.06
    	perror
    -0.06
    _called
    -0.06
    _;
↵
    -0.06
    POSITIVE LOGITS
    まと
    0.07
     фін
    0.07
    hyth
    0.06
    πέ
    0.06
    uds
    0.06
     Insp
    0.06
     crumbs
    0.06
    �
    0.06
    /product
    0.06
    .Navigator
    0.06
    Act Density 0.003%

    No Known Activations