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

    Neuronpedia

    INDEX
    Explanations

    mountains and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    give
    0.57
    м
    0.54
    १
    0.54
    ເປັນ
    0.53
     cleric
    0.53
     championed
    0.52
     चिक
    0.52
    hluk
    0.51
    ו
    0.51
     controvers
    0.51
    POSITIVE LOGITS
    _
    0.59
    覚
    0.57
     Epidemiology
    0.57
     Fight
    0.55
     Theater
    0.55
     Post
    0.54
     Thực
    0.54
     Food
    0.53
    IDA
    0.52
    یشه
    0.52
    Act Density 0.000%

    No Known Activations