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

    Neuronpedia

    INDEX
    Explanations

    SEO descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    €“
    -0.08
     Пав
    -0.07
     både
    -0.07
     >/
    -0.07
    .but
    -0.06
     організації
    -0.06
    (#
    -0.06
    ;/
    -0.06
    Researchers
    -0.06
     fred
    -0.06
    POSITIVE LOGITS
     соот
    0.06
    마
    0.06
     Fi
    0.06
     tracker
    0.06
    	cancel
    0.06
    Parcel
    0.06
     хра
    0.06
    oran
    0.06
    (MPI
    0.06
    EXPORT
    0.06
    Act Density 0.005%

    No Known Activations