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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhìn
    -0.07
    PLUGIN
    -0.07
    .dds
    -0.06
     dolay
    -0.06
    odo
    -0.06
    _LIBRARY
    -0.06
    临
    -0.06
    rug
    -0.06
    /Branch
    -0.06
    .dead
    -0.06
    POSITIVE LOGITS
     Unc
    0.07
     آنلاین
    0.07
     danske
    0.07
     emp
    0.07
    …↵↵↵↵
    0.06
     Thank
    0.06
    cons
    0.06
    kyně
    0.06
    -conf
    0.06
     decom
    0.06
    Act Density 0.027%

    No Known Activations