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

    Neuronpedia

    INDEX
    Explanations

    software modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    違
    -0.07
     ấm
    -0.07
    άντα
    -0.07
    olec
    -0.07
    bone
    -0.06
    -with
    -0.06
     judge
    -0.06
     AWS
    -0.06
     ocean
    -0.06
    oji
    -0.06
    POSITIVE LOGITS
     assured
    0.06
     reflect
    0.06
    aggregate
    0.06
    Initialization
    0.06
     scare
    0.06
     ç
    0.06
     thankful
    0.06
    Ин
    0.06
    Dos
    0.06
    (area
    0.06
    Act Density 0.028%

    No Known Activations