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

    Neuronpedia

    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .colors
    -0.06
     Chaos
    -0.06
     Vi
    -0.06
    queues
    -0.06
    yas
    -0.06
    CARD
    -0.06
     поперед
    -0.06
    _ONE
    -0.06
    .Detail
    -0.06
    .IsValid
    -0.06
    POSITIVE LOGITS
     celebrities
    0.07
     hotelu
    0.06
    /"↵
    0.06
    zeichnet
    0.06
     guests
    0.06
    -art
    0.06
    ("-
    0.06
    "`↵↵
    0.06
    [property
    0.06
    /session
    0.06
    Act Density 0.006%

    No Known Activations