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

    Neuronpedia

    INDEX
    Explanations

    select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '</
    -0.07
    .controller
    -0.06
     Quang
    -0.06
     erfolgreich
    -0.06
    .bank
    -0.06
     naked
    -0.06
    QueryString
    -0.06
     ({↵
    -0.06
    ;">
↵
    -0.06
    Mag
    -0.06
    POSITIVE LOGITS
    只能
    0.07
     вокруг
    0.06
     çevres
    0.06
    缘
    0.06
    НО
    0.06
    -builder
    0.06
    argin
    0.06
     metavar
    0.06
    øj
    0.06
    则
    0.06
    Act Density 0.010%

    No Known Activations