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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     așa
    0.83
     daños
    0.79
    দ
    0.75
     practise
    0.74
     cuarto
    0.71
    Centre
    0.71
     centre
    0.71
     characterised
    0.71
    ้ํา
    0.69
    疾
    0.68
    POSITIVE LOGITS
    MDEwOlJlcG
    0.75
    Aeonium
    0.74
    uximab
    0.73
    eonium
    0.71
    orkeling
    0.71
    iophor
    0.70
    attoo
    0.70
    bigsqcup
    0.70
    ombo
    0.69
    ropical
    0.69
    Act Density 0.000%

    No Known Activations