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

    Neuronpedia

    INDEX
    Explanations

    interfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іду
    -0.07
    edn
    -0.07
     "-",
    -0.07
     Mazda
    -0.06
     dřev
    -0.06
    .lp
    -0.06
    ruitment
    -0.06
     LAT
    -0.06
     majet
    -0.06
    PCP
    -0.06
    POSITIVE LOGITS
     interfer
    0.13
     interfere
    0.08
    !“↵↵
    0.07
     IList
    0.07
     scaleX
    0.06
    reflection
    0.06
     ।↵↵
    0.06
     confident
    0.06
     organising
    0.06
    tooltip
    0.06
    Act Density 0.001%

    No Known Activations