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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    angepicker
    -0.06
    alo
    -0.06
    Capacity
    -0.06
    oden
    -0.06
    Administrator
    -0.06
     которых
    -0.06
     Pioneer
    -0.06
    CEO
    -0.06
    Он
    -0.05
    between
    -0.05
    POSITIVE LOGITS
     analysis
    0.08
    сім
    0.07
     server
    0.07
    .Input
    0.07
     Converter
    0.06
    ึก
    0.06
    (seg
    0.06
     helps
    0.06
     ';'
    0.06
    community
    0.06
    Act Density 0.006%

    No Known Activations