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

    Neuronpedia

    INDEX
    Explanations

    System failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쒔
    -0.07
    焐
    -0.07
    掞
    -0.07
    铰
    -0.06
    שימוש
    -0.06
     FullName
    -0.06
    בסופו
    -0.06
    Active
    -0.06
    谎
    -0.06
    的话
    -0.06
    POSITIVE LOGITS
    REMOTE
    0.08
    _uri
    0.07
    庄严
    0.07
    agers
    0.07
    ティー
    0.07
    tol
    0.07
    ersistence
    0.07
     TYPE
    0.07
    _provider
    0.07
     projection
    0.07
    Act Density 0.025%

    No Known Activations