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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increases
    -0.07
    Attention
    -0.07
    ogs
    -0.07
    �
    -0.06
     goggles
    -0.06
    ​
    -0.06
     Semantic
    -0.06
    XC
    -0.06
    bies
    -0.06
    -0.06
    POSITIVE LOGITS
     ăn
    0.07
    ..."↵
    0.06
     ngOn
    0.06
    Generate
    0.06
     okres
    0.06
    .sky
    0.06
    _um
    0.06
     výkon
    0.06
    apot
    0.06
    URE
    0.06
    Act Density 0.006%

    No Known Activations