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

    Neuronpedia

    INDEX
    Explanations

    picked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хроничес
    -0.08
    mpl
    -0.08
     настройки
    -0.08
    հ
    -0.08
     шаб
    -0.08
    klass
    -0.07
     пове
    -0.07
     Ange
    -0.07
     центр
    -0.07
    idh
    -0.07
    POSITIVE LOGITS
     récol
    0.12
    Collected
    0.12
    成果
    0.10
     gathers
    0.10
     contributions
    0.10
     collected
    0.10
     accumulation
    0.10
     Contributions
    0.10
     sammeln
    0.09
     harvested
    0.09
    Act Density 0.019%

    No Known Activations