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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涵
    -0.08
    堤
    -0.07
    源源不断
    -0.07
    前提
    -0.07
    Inst
    -0.07
    تنظيف
    -0.07
     initializing
    -0.07
     propane
    -0.06
    意想不到
    -0.06
    导师
    -0.06
    POSITIVE LOGITS
     trips
    0.07
    /ec
    0.07
     reject
    0.07
    toEqual
    0.06
     Cl
    0.06
    '):↵
    0.06
    선거
    0.06
     cyc
    0.06
    .toJSON
    0.06
     cohorts
    0.06
    Act Density 0.015%

    No Known Activations