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

    Neuronpedia

    INDEX
    Explanations

    suffering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规划
    -0.07
     정책
    -0.06
     Avalanche
    -0.06
     gồm
    -0.06
     policy
    -0.06
    <n
    -0.06
    ̉
    -0.06
     stereo
    -0.06
    678
    -0.06
    toHaveBeenCalledWith
    -0.06
    POSITIVE LOGITS
     suffering
    0.08
    де
    0.08
     confines
    0.08
     distress
    0.07
    zell
    0.07
    ога
    0.07
    운데
    0.07
     highs
    0.07
    лон
    0.07
    ною
    0.06
    Act Density 0.024%

    No Known Activations