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

    Neuronpedia

    INDEX
    Explanations

    amplify and worsen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvos
    0.75
    dessous
    0.67
     листо
    0.65
     untitled
    0.65
    ➫
    0.64
    Slim
    0.63
     Altern
    0.62
     Cran
    0.62
     sillonné
    0.62
     flotte
    0.62
    POSITIVE LOGITS
     exacerb
    2.92
     exacerbate
    2.90
     exacerbated
    2.72
     amplifying
    2.60
     amplify
    2.59
     amplified
    2.53
     worsen
    2.49
     ampl
    2.45
     worsened
    2.44
     compounding
    2.41
    Act Density 0.494%

    No Known Activations