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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subconscious
    -0.07
     frustr
    -0.07
     нек
    -0.07
     disco
    -0.07
     patience
    -0.06
     služeb
    -0.06
     Ulus
    -0.06
     recal
    -0.06
     deren
    -0.06
     ludicrous
    -0.06
    POSITIVE LOGITS
    .IP
    0.07
    ISTICS
    0.06
     Prop
    0.06
    덕
    0.06
    (distance
    0.06
    PHONE
    0.06
    measurement
    0.06
    anny
    0.06
     Crowley
    0.06
    .mx
    0.06
    Act Density 0.002%

    No Known Activations