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

    Neuronpedia

    INDEX
    Explanations

    repeated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mod
    -0.07
     merged
    -0.06
    repo
    -0.06
     servo
    -0.06
    $max
    -0.06
     зависимости
    -0.06
     표시
    -0.06
    Limits
    -0.06
     Underground
    -0.06
    дается
    -0.06
    POSITIVE LOGITS
    rend
    0.07
    uture
    0.06
     tourism
    0.06
     repeatedly
    0.06
    riend
    0.06
    esting
    0.06
    (thread
    0.06
    POST
    0.06
     detainees
    0.06
    LAG
    0.06
    Act Density 0.016%

    No Known Activations