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

    Neuronpedia

    INDEX
    Explanations

    Self-worth and motivation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sleep
    -0.08
     Kiss
    -0.07
    💚
    -0.07
     concession
    -0.07
    裂缝
    -0.07
     plataforma
    -0.07
    ]<=
    -0.07
    -author
    -0.06
     oxy
    -0.06
     missed
    -0.06
    POSITIVE LOGITS
     setType
    0.07
    你能
    0.07
     Variety
    0.07
    很难
    0.07
    ots
    0.07
    类别
    0.07
    pts
    0.07
    事业
    0.07
    special
    0.06
    uns
    0.06
    Act Density 0.060%

    No Known Activations