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

    Neuronpedia

    INDEX
    Explanations

    TNF research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paz
    -0.68
    pertory
    -0.67
    JV
    -0.57
    KK
    -0.52
     ag
    -0.50
     pul
    -0.47
     Bet
    -0.45
     D
    -0.43
     sta
    -0.43
     cor
    -0.43
    POSITIVE LOGITS
     незавершена
    1.11
    InstanceState
    0.81
    AnchorStyles
    0.81
     myſelf
    0.79
    ]")]
    0.77
    OrNil
    0.75
     rayures
    0.74
     EnglishChoose
    0.74
    anyahu
    0.73
    contentLoaded
    0.73
    Act Density 0.042%

    No Known Activations