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

    Neuronpedia

    INDEX
    Explanations

    gemma google deepmind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elegantly
    0.46
     acclaim
    0.46
    allelujah
    0.44
     auspicious
    0.43
     elegant
    0.43
     graceful
    0.43
     pushed
    0.42
     rollercoaster
    0.41
     timeless
    0.41
     accolades
    0.41
    POSITIVE LOGITS
     Schools
    0.48
    ництва
    0.47
     Desarrollo
    0.43
    schools
    0.43
     Colegio
    0.43
    gevens
    0.42
     Escola
    0.42
     DETER
    0.42
    హ
    0.42
     Libraries
    0.41
    Act Density 0.001%

    No Known Activations