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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chod
    -0.07
     cancell
    -0.07
     sł
    -0.06
     continua
    -0.06
     freight
    -0.06
    _MAN
    -0.06
     salary
    -0.06
     cancellation
    -0.06
     Та
    -0.06
     emulation
    -0.06
    POSITIVE LOGITS
     Roberts
    0.06
     confronting
    0.06
    InnerHTML
    0.06
    нож
    0.06
    <>();
↵
    0.06
    eter
    0.06
    jpg
    0.06
    dbl
    0.06
    .tif
    0.06
     Lua
    0.06
    Act Density 0.012%

    No Known Activations