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

    Neuronpedia

    INDEX
    Explanations

    Lists of concepts and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesar
    0.48
    orin
    0.48
     der
    0.46
    us
    0.46
     visual
    0.46
     screenshots
    0.45
    ird
    0.45
    不论
    0.45
    radio
    0.44
     radio
    0.44
    POSITIVE LOGITS
    Roses
    0.45
     遊ん
    0.45
    ิติ
    0.45
     遅く
    0.45
     санти
    0.43
    Cry
    0.43
     contaminate
    0.43
    𝓑
    0.41
    Mile
    0.40
     सैयद
    0.40
    Act Density 0.001%

    No Known Activations