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

    Neuronpedia

    INDEX
    Explanations

    baseline correction or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exp
    0.39
     esche
    0.39
    폈
    0.38
    емая
    0.38
     enmity
    0.38
     تد
    0.38
    zia
    0.38
     entreprene
    0.37
    രംഭ
    0.37
     ஆரம்பித்த
    0.37
    POSITIVE LOGITS
     baseline
    0.48
     基
    0.42
    baseline
    0.41
     indicator
    0.40
    Baseline
    0.40
    Ide
    0.39
     Baseline
    0.39
    Bas
    0.38
    基
    0.37
     Ideas
    0.37
    Act Density 0.000%

    No Known Activations