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

    Neuronpedia

    INDEX
    Explanations

    promotional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pass
    -0.07
     ман
    -0.06
     schemas
    -0.06
     merit
    -0.06
     citing
    -0.06
    .basic
    -0.06
     คาส
    -0.06
     convers
    -0.06
    Fire
    -0.06
     chua
    -0.06
    POSITIVE LOGITS
     supers
    0.08
     Californ
    0.07
    port
    0.07
    -Pro
    0.06
     oscill
    0.06
     Mp
    0.06
    不是
    0.06
     Nẵng
    0.06
    getService
    0.06
    -style
    0.06
    Act Density 0.032%

    No Known Activations