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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faster
    -0.07
     Bones
    -0.06
    Safe
    -0.06
     Connecting
    -0.06
    igate
    -0.06
     Ravens
    -0.06
    .Registry
    -0.06
     यद
    -0.06
    CM
    -0.06
     Dark
    -0.06
    POSITIVE LOGITS
    ;if
    0.06
     своими
    0.06
     thương
    0.06
     distingu
    0.06
    alfa
    0.06
    poster
    0.06
    arus
    0.06
     Worce
    0.06
    imensional
    0.06
     قهر
    0.06
    Act Density 0.010%

    No Known Activations