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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pl
    -0.07
    tri
    -0.07
    ulp
    -0.07
    085
    -0.06
    017
    -0.06
    016
    -0.06
     cart
    -0.06
     xử
    -0.06
    076
    -0.06
    015
    -0.06
    POSITIVE LOGITS
    $ret
    0.07
     관심
    0.07
    .ff
    0.07
    集中
    0.07
     �
    0.06
     Take
    0.06
     kèo
    0.06
    .listen
    0.06
     �
    0.06
    .Now
    0.06
    Act Density 0.055%

    No Known Activations