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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STR
    -0.06
    mui
    -0.06
     carriers
    -0.06
    one
    -0.06
    REQ
    -0.06
    루
    -0.06
     Img
    -0.05
    ptest
    -0.05
     age
    -0.05
     obstacle
    -0.05
    POSITIVE LOGITS
    대의
    0.08
     MAL
    0.07
    三三三三
    0.07
    Private
    0.07
    結婚
    0.07
     곧
    0.06
    notify
    0.06
     информа
    0.06
    окрема
    0.06
    震
    0.06
    Act Density 0.574%

    No Known Activations