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

    Neuronpedia

    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gecko
    -0.08
     Confidential
    -0.07
     geld
    -0.07
    assing
    -0.07
     Communist
    -0.07
    -ce
    -0.07
     peacefully
    -0.07
     দ্বিতীয়
    -0.07
     Seigneur
    -0.07
    -billion
    -0.07
    POSITIVE LOGITS
     tweaks
    0.11
    调整
    0.11
     tweaking
    0.11
     adjustments
    0.11
     adjustment
    0.11
     усил
    0.10
     tweak
    0.10
     boosting
    0.10
     Enhance
    0.10
     enhancement
    0.10
    Act Density 0.007%

    No Known Activations