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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TMP
    -0.07
    (Resources
    -0.07
    bright
    -0.06
     pure
    -0.06
     Proj
    -0.06
    Labour
    -0.06
     okul
    -0.06
    stud
    -0.06
     博
    -0.06
     needles
    -0.06
    POSITIVE LOGITS
     사이트
    0.07
    авлива
    0.07
    ino
    0.07
    ासन
    0.06
     specification
    0.06
     solution
    0.06
     Sections
    0.06
    ITT
    0.06
     comentario
    0.06
    uts
    0.06
    Act Density 0.001%

    No Known Activations