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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    소를
    -0.07
    .OK
    -0.07
     PNG
    -0.07
    。お
    -0.07
     фут
    -0.06
    '].$
    -0.06
     Laravel
    -0.06
    .lastname
    -0.06
    	ax
    -0.06
    colon
    -0.06
    POSITIVE LOGITS
     Seller
    0.07
     inclined
    0.07
    _ep
    0.06
     meth
    0.06
     degree
    0.06
    ramer
    0.06
    odon
    0.06
    フト
    0.06
     constituent
    0.06
     Educational
    0.06
    Act Density 0.000%

    No Known Activations