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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .credit
    -0.07
    	graph
    -0.07
    dbName
    -0.07
    -stars
    -0.07
    /
↵
↵
    -0.06
     wollte
    -0.06
    .Notification
    -0.06
    CompatActivity
    -0.06
    .leave
    -0.06
     也
    -0.06
    POSITIVE LOGITS
     Maur
    0.07
     consolidated
    0.06
     Mechanics
    0.06
     صح
    0.06
     MG
    0.06
     haha
    0.06
     harvesting
    0.06
    onec
    0.06
     Dynamo
    0.06
    тер
    0.05
    Act Density 0.000%

    No Known Activations