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

    Neuronpedia

    INDEX
    Explanations

    risk mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.77
    az
    0.72
    ears
    0.71
    od
    0.67
    onian
    0.66
    ০০
    0.65
    ার্থে
    0.64
    ંગ
    0.64
    ému
    0.64
    ook
    0.63
    POSITIVE LOGITS
     ფორ
    0.87
     eten
    0.83
     apporter
    0.83
    컴
    0.82
    för
    0.80
     noten
    0.80
    nach
    0.79
     endast
    0.79
     lungo
    0.76
     vendre
    0.76
    Act Density 0.357%

    No Known Activations