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

    Neuronpedia

    INDEX
    Explanations

    XR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conten
    -0.08
    ots
    -0.07
    downloads
    -0.07
     Scotland
    -0.07
     Ventura
    -0.06
     councils
    -0.06
     ابتدا
    -0.06
     ghetto
    -0.06
    post
    -0.06
     guideline
    -0.06
    POSITIVE LOGITS
     �
    0.07
     αντι
    0.07
    люч
    0.07
     ゝ
    0.06
    _UI
    0.06
     примен
    0.06
    ={(
    0.06
    tility
    0.06
     �
    0.06
    ực
    0.06
    Act Density 0.012%

    No Known Activations