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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    observe
    -0.06
    _G
    -0.06
    .padding
    -0.06
    PART
    -0.06
    ropping
    -0.06
    lost
    -0.05
    르고
    -0.05
     relation
    -0.05
    plier
    -0.05
    Trail
    -0.05
    POSITIVE LOGITS
     خصوص
    0.08
     Estates
    0.07
     rhythms
    0.07
    every
    0.07
    FM
    0.07
     Rogers
    0.07
    ández
    0.07
     ha
    0.07
     innoc
    0.06
    Miller
    0.06
    Act Density 0.040%

    No Known Activations