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

    Neuronpedia

    INDEX
    Explanations

    PM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     batching
    -0.08
     objection
    -0.08
     présenté
    -0.07
    (ExpectedConditions
    -0.07
     Bücher
    -0.07
     lipstick
    -0.07
     Sanity
    -0.07
     infringement
    -0.07
     André
    -0.07
     protagonist
    -0.07
    POSITIVE LOGITS
    ailles
    0.09
    Triangles
    0.07
    עלות
    0.07
    floor
    0.07
    earer
    0.07
     placing
    0.07
    缝
    0.07
    퍠
    0.07
    holder
    0.07
    kap
    0.07
    Act Density 0.006%

    No Known Activations