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

    Neuronpedia

    INDEX
    Explanations

    weak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *)↵
    -0.08
     arranging
    -0.08
     contratar
    -0.08
     ************************
    -0.07
     taxonomy
    -0.07
     kwest
    -0.07
     rtl
    -0.07
     ocean
    -0.07
     routes
    -0.07
     turístico
    -0.07
    POSITIVE LOGITS
    aupun
    0.08
    hede
    0.08
     Fitz
    0.08
     Juvent
    0.07
     Kagame
    0.07
     Unión
    0.07
     guerr
    0.07
     стер
    0.07
    quam
    0.07
    quées
    0.07
    Act Density 0.001%

    No Known Activations