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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Restaurant
    -0.07
     sant
    -0.07
     Bad
    -0.07
    Almost
    -0.07
     TIMEOUT
    -0.07
     organizations
    -0.07
     Laf
    -0.06
     kissing
    -0.06
    _Tool
    -0.06
     Governments
    -0.06
    POSITIVE LOGITS
    “We
    0.07
    <ul
    0.07
    _UDP
    0.06
     glean
    0.06
     combin
    0.06
     semiclassical
    0.06
    غط
    0.06
    );">↵
    0.06
    ICK
    0.06
     εμπ
    0.06
    Act Density 0.000%

    No Known Activations