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

    Neuronpedia

    INDEX
    Explanations

    Did you know?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    มีการ
    0.71
    ï
    0.68
     paws
    0.68
     paw
    0.67
    성화
    0.64
    ிகளைக்
    0.63
     cannot
    0.62
    တွေ
    0.60
    throw
    0.59
    어로
    0.59
    POSITIVE LOGITS
     Oxidation
    0.80
    oyloxy
    0.80
    স্ব
    0.79
     შემთხვევ
    0.77
    znej
    0.77
    ↵↵
    0.77
    褸
    0.76
    othelium
    0.76
    𝐳
    0.75
     スチール
    0.73
    Act Density 0.000%

    No Known Activations