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

    Neuronpedia

    INDEX
    Explanations

    say "self"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bert
    -0.06
     libr
    -0.06
     Extreme
    -0.06
    City
    -0.06
     Oman
    -0.06
    histoire
    -0.06
    OT
    -0.06
     similarly
    -0.06
     tap
    -0.06
     November
    -0.06
    POSITIVE LOGITS
     multer
    0.07
     physic
    0.06
    ασίας
    0.06
    /target
    0.06
     visa
    0.06
    вай
    0.06
    esser
    0.06
     CTL
    0.06
    arket
    0.06
    ////////////////////////////////////////////////////////////////
    0.06
    Act Density 0.008%

    No Known Activations