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

    Neuronpedia

    INDEX
    Explanations

    to share, create, prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.52
    炤
    0.52
    ナトリウム
    0.50
    数
    0.50
    жна
    0.49
    市場
    0.48
    岃
    0.48
    ين
    0.48
    いつ
    0.48
     ремон
    0.47
    POSITIVE LOGITS
    of
    0.53
    info
    0.49
    \.
    0.48
    com
    0.46
    yect
    0.46
    usc
    0.45
    ứt
    0.45
     Com
    0.44
    ci
    0.44
    urov
    0.44
    Act Density 0.000%

    No Known Activations