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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apl
    -0.07
     AB
    -0.07
     harbor
    -0.07
    .serv
    -0.07
    Hint
    -0.06
     Heroes
    -0.06
     agony
    -0.06
    ependency
    -0.06
    _axes
    -0.06
    rink
    -0.06
    POSITIVE LOGITS
     süreci
    0.07
    _hresult
    0.07
    čně
    0.06
     mı
    0.06
    による
    0.06
     Amazing
    0.06
    šní
    0.06
    ):?>↵
    0.06
    جل
    0.06
    adır
    0.06
    Act Density 0.001%

    No Known Activations