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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abstraction
    -0.07
    Tim
    -0.06
    RF
    -0.06
    el
    -0.06
     تهران
    -0.06
    enment
    -0.06
    udio
    -0.06
    AL
    -0.06
    integration
    -0.06
    ering
    -0.06
    POSITIVE LOGITS
     заключ
    0.07
    .fromFunction
    0.07
    Existing
    0.07
    =__
    0.06
     مطال
    0.06
    ://'
    0.06
     SEND
    0.06
     nouvelle
    0.06
    Ensure
    0.06
    /testify
    0.06
    Act Density 0.030%

    No Known Activations