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

    Neuronpedia

    INDEX
    Explanations

    lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کاری
    -0.07
    名称
    -0.06
    ldr
    -0.06
    Elements
    -0.06
    Skills
    -0.06
     美国
    -0.06
    .any
    -0.06
    aptop
    -0.06
     conservative
    -0.06
     compl
    -0.06
    POSITIVE LOGITS
     stark
    0.07
    (dist
    0.07
     Sphinx
    0.06
     deductions
    0.06
     grunt
    0.06
    τερο
    0.06
     zahl
    0.06
    *K
    0.06
    .rstrip
    0.06
     getopt
    0.06
    Act Density 0.011%

    No Known Activations