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

    Neuronpedia

    INDEX
    Explanations

    Social media/accounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grove
    -0.07
     female
    -0.06
    _STORAGE
    -0.06
     medios
    -0.06
    nees
    -0.06
    .students
    -0.06
    арт
    -0.06
     numRows
    -0.06
    .weights
    -0.06
    _module
    -0.06
    POSITIVE LOGITS
     prevail
    0.07
     Bra
    0.07
     yaşan
    0.07
    ая
    0.06
     interrog
    0.06
     Signing
    0.06
    glomer
    0.06
     Pierre
    0.06
     ανα
    0.06
    ضا
    0.06
    Act Density 0.181%

    No Known Activations