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

    Neuronpedia

    INDEX
    Explanations

    I should, I think, I know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रदान
    0.42
    Designed
    0.42
    Cannot
    0.41
     diseñada
    0.41
     فراہم
    0.40
    Suggest
    0.40
    Rationale
    0.40
    ामो
    0.39
    FARE
    0.39
     сада
    0.39
    POSITIVE LOGITS
     try
    0.52
    try
    0.52
     even
    0.49
     should
    0.48
     даже
    0.47
     sogar
    0.45
     zelfs
    0.45
     навіть
    0.45
     hope
    0.44
     nadzie
    0.44
    Act Density 0.000%

    No Known Activations