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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .layout
    -0.07
    ARI
    -0.06
     brushes
    -0.06
    NODE
    -0.06
    温
    -0.06
    ari
    -0.06
    -indent
    -0.06
    (latitude
    -0.06
     Hari
    -0.06
     Examples
    -0.06
    POSITIVE LOGITS
     Jeep
    0.07
     کلاس
    0.06
     inplace
    0.06
    TRL
    0.06
    。↵
    0.06
     злоч
    0.06
    0.06
    한
    0.06
     قول
    0.06
     Leipzig
    0.05
    Act Density 0.093%

    No Known Activations