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

    Neuronpedia

    INDEX
    Explanations

    super or base

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Appearance
    -0.08
    ams
    -0.07
    沈
    -0.06
    >↵
    -0.06
    /light
    -0.06
     dispozici
    -0.06
    (change
    -0.06
    !”↵↵
    -0.06
    _builder
    -0.06
     strike
    -0.06
    POSITIVE LOGITS
    。「
    0.06
     USSR
    0.06
     preceding
    0.06
    <Post
    0.06
    (Number
    0.06
     insanlar
    0.06
    orderby
    0.06
     terug
    0.06
     indeb
    0.06
     onPostExecute
    0.06
    Act Density 0.006%

    No Known Activations