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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .xyz
    -0.07
     sec
    -0.07
    COLOR
    -0.06
     Prim
    -0.06
     gram
    -0.06
     baj
    -0.06
     number
    -0.06
     beauty
    -0.06
    ¾
    -0.06
    busters
    -0.06
    POSITIVE LOGITS
    lyphicon
    0.08
    elopment
    0.07
     sebeb
    0.07
    >k
    0.07
     воздейств
    0.06
    trl
    0.06
    incoming
    0.06
     выгляд
    0.06
    ensual
    0.06
     sesame
    0.06
    Act Density 0.023%

    No Known Activations