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

    Neuronpedia

    INDEX
    Explanations

    affordable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    0.55
    ano
    0.53
    ayama
    0.53
    ле
    0.52
    ole
    0.52
    r
    0.52
    tell
    0.51
    не
    0.51
    ør
    0.50
    å
    0.50
    POSITIVE LOGITS
    精灵
    0.46
     essences
    0.43
    其他
    0.42
     doctrines
    0.41
    র্গের
    0.41
     incompetence
    0.41
    不能为空
    0.41
     counterfeit
    0.40
    ！」
    0.40
     insurgents
    0.40
    Act Density 0.000%

    No Known Activations