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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “It
    -0.08
     feasibility
    -0.07
     expansion
    -0.07
    .host
    -0.06
    каз
    -0.06
     Expansion
    -0.06
     finalists
    -0.06
    Customer
    -0.06
     mercy
    -0.06
     ----------------
    -0.06
    POSITIVE LOGITS
        ↵↵↵
    0.07
    ]:↵↵↵
    0.07
    Cisco
    0.06
    ､:
    0.06
     цій
    0.06
    .nio
    0.06
    glomer
    0.06
    ViewById
    0.06
    ↵      ↵
    0.06
    released
    0.06
    Act Density 0.004%

    No Known Activations