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

    Neuronpedia

    INDEX
    Explanations

    Storing samples at temperatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticed
    -0.07
     Hello
    -0.07
    별
    -0.06
    _joint
    -0.06
     lesion
    -0.06
    Triangles
    -0.06
     Stud
    -0.06
     arterial
    -0.06
    ddie
    -0.06
     lesions
    -0.06
    POSITIVE LOGITS
    _flash
    0.07
     Plug
    0.07
    ате
    0.06
    lomou
    0.06
    (cps
    0.06
     Athe
    0.06
     Manufact
    0.06
    .can
    0.06
     lỗi
    0.06
     експ
    0.06
    Act Density 0.008%

    No Known Activations