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

    Neuronpedia

    INDEX
    Explanations

    course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    0.47
     podczas
    0.45
    ATES
    0.45
    лія
    0.45
    िड
    0.43
    during
    0.43
    ENUM
    0.43
    CP
    0.42
    Activate
    0.42
    トレーニング
    0.42
    POSITIVE LOGITS
     vegetarian
    0.51
     diversifying
    0.50
     malonyl
    0.50
     divergent
    0.49
     beaded
    0.49
     clonal
    0.49
     parab
    0.49
     curving
    0.48
     day
    0.48
     microbes
    0.48
    Act Density 0.003%

    No Known Activations