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

    Neuronpedia

    INDEX
    Explanations

    suppress or inhibit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాల్సి
    0.44
     एके
    0.42
    徝
    0.40
     Byl
    0.37
    рного
    0.37
     Deine
    0.37
     Powered
    0.36
     Dis
    0.36
     Tener
    0.36
    ärte
    0.36
    POSITIVE LOGITS
     suppressing
    1.03
     suppress
    1.01
     suppression
    1.01
     suppressed
    0.96
     suppresses
    0.96
    Suppress
    0.89
     Suppression
    0.88
    抑制
    0.84
     suppressor
    0.78
    抑
    0.76
    Act Density 0.000%

    No Known Activations