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

    Neuronpedia

    INDEX
    Explanations

    talk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fruition
    -0.07
    uent
    -0.07
     Iris
    -0.07
     pond
    -0.06
     Civ
    -0.06
    ượ
    -0.06
    venience
    -0.06
    ınca
    -0.06
     yPos
    -0.06
     ();
↵
    -0.06
    POSITIVE LOGITS
    Talk
    0.08
    tok
    0.08
     talk
    0.08
     Talk
    0.07
    .work
    0.07
    .Work
    0.07
     Mash
    0.07
     알아
    0.07
    مال
    0.07
    mg
    0.07
    Act Density 0.019%

    No Known Activations