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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tried
    -0.07
     ordinance
    -0.06
    .scrollHeight
    -0.06
     औ
    -0.06
     neben
    -0.06
    <boolean
    -0.06
     Москва
    -0.06
    zM
    -0.06
    Ord
    -0.06
     دید
    -0.06
    POSITIVE LOGITS
    #aa
    0.08
    creation
    0.08
     dating
    0.07
     handic
    0.07
    specified
    0.07
     Bowie
    0.07
     dates
    0.07
     سن
    0.07
    $client
    0.07
     mim
    0.06
    Act Density 0.006%

    No Known Activations