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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toHaveBeenCalledWith
    -0.07
    Iteration
    -0.07
    /****************************************
    -0.07
    aggable
    -0.07
     slavery
    -0.07
     condensed
    -0.07
     satisfaction
    -0.07
    Calcul
    -0.06
     Temporary
    -0.06
    Bloc
    -0.06
    POSITIVE LOGITS
    Mart
    0.07
    -pt
    0.06
    igit
    0.06
     sg
    0.06
     stor
    0.06
     cuer
    0.06
     stirred
    0.06
     ベ
    0.06
    /pkg
    0.05
     pid
    0.05
    Act Density 0.010%

    No Known Activations