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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucher
    -0.08
     lương
    -0.07
     itm
    -0.07
     itching
    -0.07
    土地
    -0.06
     cpp
    -0.06
     Erick
    -0.06
     사랑
    -0.06
    certificate
    -0.06
     Fisheries
    -0.06
    POSITIVE LOGITS
    '],$_
    0.07
     태
    0.07
    Bind
    0.06
    _att
    0.06
    FFF
    0.06
    /inc
    0.06
     Cherry
    0.06
     replied
    0.06
    ğını
    0.06
     Nat
    0.06
    Act Density 0.007%

    No Known Activations