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

    Neuronpedia

    INDEX
    Explanations

    related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Noon
    -0.07
     Fritz
    -0.07
     lac
    -0.06
    etí
    -0.06
    .discount
    -0.06
     Ikea
    -0.06
     ков
    -0.06
     Sanct
    -0.06
    toy
    -0.06
     KO
    -0.06
    POSITIVE LOGITS
     related
    0.07
     intertwined
    0.07
    उत
    0.06
    cached
    0.06
    лада
    0.06
    	world
    0.06
    adoras
    0.06
    .Misc
    0.06
    currently
    0.06
    esting
    0.06
    Act Density 0.012%

    No Known Activations