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

    Neuronpedia

    INDEX
    Explanations

    difficulty or impossibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preguntas
    0.43
     nécess
    0.43
     wymag
    0.42
     että
    0.41
    ว่า
    0.39
     membutuhkan
    0.39
     undertakings
    0.39
     contradictions
    0.38
     requires
    0.38
    മ്പോൾ
    0.38
    POSITIVE LOGITS
     impossible
    0.57
    impossible
    0.51
     costly
    0.49
     imposible
    0.46
    昂
    0.41
     Impossible
    0.41
    empel
    0.39
    expensive
    0.39
    lıkla
    0.39
     impossibile
    0.39
    Act Density 0.021%

    No Known Activations