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

    Neuronpedia

    INDEX
    Explanations

    longer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    業
    -0.07
     meme
    -0.06
    ็อต
    -0.06
     Hook
    -0.06
     İb
    -0.06
     mainScreen
    -0.06
    rale
    -0.06
    &t
    -0.06
     政
    -0.06
    ocument
    -0.06
    POSITIVE LOGITS
    ัตร
    0.07
    ountain
    0.07
    uela
    0.06
    _ENCODE
    0.06
     전국
    0.06
     :-)
    0.06
    regs
    0.06
     overpower
    0.06
     versatility
    0.06
    南省
    0.06
    Act Density 0.212%

    No Known Activations