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

    Neuronpedia

    INDEX
    Explanations

    UTC/GMT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     No
    -0.07
    十三
    -0.07
    .FIELD
    -0.07
    的大
    -0.07
    แสง
    -0.07
    북도
    -0.06
    (txt
    -0.06
     Saturdays
    -0.06
    .Method
    -0.06
    :animated
    -0.06
    POSITIVE LOGITS
     internals
    0.07
    iges
    0.07
     "+↵
    0.07
     skirm
    0.06
     kriz
    0.06
     happier
    0.06
     Å
    0.06
     taxonomy
    0.06
     crunch
    0.06
    straints
    0.05
    Act Density 0.004%

    No Known Activations