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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Hour
    -0.08
     origins
    -0.07
    Death
    -0.07
    需
    -0.07
    자
    -0.07
    Tap
    -0.06
    .days
    -0.06
    아이
    -0.06
     awhile
    -0.06
     Success
    -0.06
    POSITIVE LOGITS
    Alabama
    0.08
    \Template
    0.06
    ousy
    0.06
    ABI
    0.06
     wander
    0.06
     plywood
    0.06
    QueryString
    0.06
    _solve
    0.06
    insk
    0.06
    LONG
    0.06
    Act Density 0.044%

    No Known Activations