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

    Neuronpedia

    INDEX
    Explanations

    violations and requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpDown
    -0.07
    锋
    -0.07
    _Target
    -0.07
    ]")]↵
    -0.06
     ihr
    -0.06
    SCR
    -0.06
    EventHandler
    -0.06
    chl
    -0.06
    .direction
    -0.06
     perpetual
    -0.06
    POSITIVE LOGITS
     może
    0.06
     PLL
    0.06
    坡
    0.06
    dash
    0.06
    фик
    0.06
     kaz
    0.06
     И
    0.05
    =q
    0.05
    mouse
    0.05
     disgrace
    0.05
    Act Density 0.004%

    No Known Activations