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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debating
    -0.07
    高
    -0.06
     unlocking
    -0.06
     Friends
    -0.06
     certification
    -0.06
     Accounting
    -0.06
    ैस
    -0.06
     registrar
    -0.06
    Friends
    -0.06
     mest
    -0.06
    POSITIVE LOGITS
    fillType
    0.07
    .…↵↵
    0.07
     هستند
    0.06
     znění
    0.06
     pp
    0.06
    (rename
    0.06
    .initializeApp
    0.06
    pellier
    0.06
    =edge
    0.06
    -add
    0.06
    Act Density 0.251%

    No Known Activations