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

    Neuronpedia

    INDEX
    Explanations

    thriller, Harry, desktop, change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    啰
    0.50
    the
    0.47
    逶
    0.46
    टाम
    0.46
    do
    0.46
    txt
    0.45
     Drilling
    0.45
    
    0.45
    rtel
    0.44
    डॉ
    0.44
    POSITIVE LOGITS
     измени
    0.56
     изменить
    0.52
     সালমান
    0.45
     propose
    0.44
     cease
    0.44
     cambio
    0.43
     дизайне
    0.43
     zmienia
    0.43
    ᱓
    0.43
     mwen
    0.42
    Act Density 0.003%

    No Known Activations