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

    Neuronpedia

    INDEX
    Explanations

    see the words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     configura
    0.57
     Оста
    0.56
     оста
    0.52
     diverses
    0.50
    ঵
    0.50
    侙
    0.50
    保証
    0.49
    ᕇ
    0.49
     ذریعہ
    0.49
    䯩
    0.49
    POSITIVE LOGITS
    p
    0.54
    r
    0.52
    women
    0.50
    h
    0.47
    tracking
    0.44
    n
    0.44
    flowers
    0.43
    deoxy
    0.43
    ochemistry
    0.42
    deformation
    0.42
    Act Density 0.005%

    No Known Activations