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

    Neuronpedia

    INDEX
    Explanations

    interact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marian
    -0.07
    Please
    -0.06
    .published
    -0.06
    -One
    -0.06
    Ptr
    -0.06
     корист
    -0.06
    Poor
    -0.06
    awns
    -0.06
    174
    -0.06
    	My
    -0.06
    POSITIVE LOGITS
    _tm
    0.07
    ارية
    0.07
    robat
    0.06
    \Template
    0.06
     rape
    0.06
     underlying
    0.06
    รายงาน
    0.06
     băng
    0.06
    bsd
    0.06
    驾
    0.06
    Act Density 0.024%

    No Known Activations