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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     місці
    -0.07
    Handles
    -0.06
     Kaplan
    -0.06
     resolver
    -0.06
     Overrides
    -0.06
     Notify
    -0.06
     demographics
    -0.06
    (parsed
    -0.06
    Cluster
    -0.06
     pred
    -0.06
    POSITIVE LOGITS
     Comprehensive
    0.07
     Provide
    0.06
    нивер
    0.06
     мон
    0.06
    leton
    0.06
    >Hello
    0.06
    �新
    0.06
     understandably
    0.06
    ajo
    0.06
    bih
    0.06
    Act Density 0.040%

    No Known Activations