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

    Neuronpedia

    INDEX
    Explanations

    NJ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    其实
    -0.07
    ESTAMP
    -0.07
     
    -0.07
    caffold
    -0.07
     pointers
    -0.06
    _U
    -0.06
    .vert
    -0.06
     enzymes
    -0.06
    ine
    -0.06
    Trigger
    -0.06
    POSITIVE LOGITS
    ству
    0.07
     veriyor
    0.07
     الرو
    0.07
     opi
    0.06
     cleans
    0.06
    內
    0.06
    -Sah
    0.06
    스로
    0.06
    educ
    0.06
     sovere
    0.06
    Act Density 0.047%

    No Known Activations