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

    Neuronpedia

    INDEX
    Explanations

    harmless AI assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gorges
    0.79
    ting
    0.75
    urgy
    0.73
    ${
    0.72
    tedir
    0.72
    toList
    0.70
     retouch
    0.70
    rouge
    0.69
    akur
    0.66
    gdf
    0.65
    POSITIVE LOGITS
     Ј
    0.78
     в
    0.78
     creativo
    0.75
     podido
    0.74
    ба
    0.74
     respectiv
    0.74
     efectiva
    0.73
     цього
    0.73
     こちら
    0.73
     admite
    0.72
    Act Density 0.019%

    No Known Activations