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

    Neuronpedia

    INDEX
    Explanations

    lifecycle methodologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hesia
    0.70
    
    0.67
    ী
    0.66
    acy
    0.65
     画像
    0.65
    ↵↵
    0.62
    可能です
    0.62
    δε
    0.62
    ādi
    0.60
    ام
    0.59
    POSITIVE LOGITS
    potato
    0.93
     strontium
    0.93
     semifinal
    0.89
     DTS
    0.89
     subplot
    0.89
     postulate
    0.88
     gooey
    0.88
    HANDLER
    0.86
     molyb
    0.86
     grout
    0.86
    Act Density 0.001%

    No Known Activations