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

    Neuronpedia

    INDEX
    Explanations

    comparisons and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tablets
    -0.07
     homeschool
    -0.06
    220
    -0.06
     Spielberg
    -0.06
     yem
    -0.06
    _CO
    -0.06
    _sources
    -0.06
    .centerX
    -0.06
     Semantic
    -0.06
    うち
    -0.06
    POSITIVE LOGITS
     asteroid
    0.09
     pard
    0.07
    �다
    0.06
     kapat
    0.06
     boz
    0.06
     instr
    0.06
    Meal
    0.06
     Patrick
    0.06
    *****
↵
    0.06
    个人
    0.06
    Act Density 0.047%

    No Known Activations