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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .deleted
    -0.07
    	project
    -0.07
     tomb
    -0.06
     routing
    -0.06
    史
    -0.06
    ociety
    -0.06
    Alternate
    -0.06
    Whenever
    -0.06
    fill
    -0.06
    stup
    -0.06
    POSITIVE LOGITS
     ومع
    0.07
     luaL
    0.06
     تسم
    0.06
    ヨ
    0.06
    ίνα
    0.06
    아
    0.06
    _MR
    0.06
     designate
    0.06
     ／:
    0.06
    еч
    0.06
    Act Density 0.000%

    No Known Activations